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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70258
    Prev
    Next
    INDEX
    Explanations

    financial constraints, possession, programme

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

    The neuron fires on named entities (people, places) and numeric or measurement expressions.

    oai_token-act-pair · o4-miniTriggered 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
    -1.76
     not
    -1.63
    <bos>
    -1.59
     plastered
    -1.57
     just
    -1.55
    4
    -1.47
     its
    -1.41
    簷
    -1.39
    5
    -1.36
    -"
    -1.29
    POSITIVE LOGITS
    )”.
    1.60
    なので
    1.48
    ”]
    1.45
     firſt
    1.42
    ”).
    1.41
     publicités
    1.38
     に関する
    1.38
    ’:
    1.35
    嫱
    1.32
    aneity
    1.31
    Activations Density 0.004%

    No Known Activations