© 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. 1226
    Prev
    Next
    INDEX
    Explanations

    by [agent/origin]

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    obviously
    -2.06
    {
    -2.02
    acterísticas
    -1.88
    usually
    -1.84
     cuatro
    -1.84
    generally
    -1.83
    什么时候
    -1.82
     predominantly
    -1.82
     deliciously
    -1.82
     wist
    -1.80
    POSITIVE LOGITS
     because
    2.09
     Because
    2.09
     by
    2.06
     for
    1.96
     their
    1.86
     from
    1.84
     Even
    1.84
     Since
    1.82
     give
    1.81
     Seems
    1.78
    Activations Density 0.051%

    No Known Activations