© 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. 34-GEMMASCOPE-RES-131K
    7. 81040
    Prev
    Next
    INDEX
    Explanations

    legal phrases and names

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

    This neuron responds to C-style import directives, i.e. the “#include <…>” header‐inclusion tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    见
    -0.87
    اسة
    -0.85
     juzg
    -0.82
     kehilangan
    -0.82
    }}}
    -0.82
    tiven
    -0.82
     梦
    -0.82
     tř
    -0.80
    cled
    -0.79
    }).
    -0.79
    POSITIVE LOGITS
     cambiamento
    0.75
    idia
    0.75
     beginning
    0.73
     gazing
    0.73
    运用
    0.72
    propTypes
    0.72
     acceptable
    0.70
     aspetto
    0.70
     appreciation
    0.69
     publics
    0.69
    Activations Density 0.001%

    No Known Activations