© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47505
    Prev
    Next
    INDEX
    Explanations

    incremental development or addition

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on every occurrence of the word “incremental.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    descriptions of gradual, step-by-step increases, additions, or development.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "incremental" in technical or formal contexts describing gradual changes, additions, or increases.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     But
    -3.11
     但
    -2.88
    }$
    -2.80
    2
    -2.77
    9
    -2.73
    是
    -2.73
    }
    -2.63
    E
    -2.44
    <i>
    -2.42
    to
    -2.41
    POSITIVE LOGITS
    vantaged
    2.45
    nın
    2.44
    芣
    2.42
    ют
    2.39
    踅
    2.33
     morte
    2.30
    摃
    2.30
     camiset
    2.22
    紧接着
    2.22
     deliciosa
    2.20
    Activations Density 0.004%

    No Known Activations