© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58298
    Prev
    Next
    INDEX
    Explanations

    reading

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

    The neuron strongly lights up on terms used in scholarly or critical discussion—words having to do with analysis and interpretation of texts (e.g. lenses, value, identify, read, criticism).

    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
    builtin
    -0.89
     adj
    -0.86
     remarqu
    -0.85
     camioneta
    -0.84
    ya
    -0.84
    债
    -0.83
     kife
    -0.83
    韮
    -0.83
     expres
    -0.82
     eint
    -0.81
    POSITIVE LOGITS
     reading
    2.23
     readings
    1.85
    Reading
    1.79
    reading
    1.74
     reader
    1.73
     readers
    1.67
     reread
    1.61
     Reading
    1.52
     reception
    1.52
     чита
    1.52
    Activations Density 0.023%

    No Known Activations