© 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. 22-GEMMASCOPE-RES-131K
    7. 68476
    Prev
    Next
    INDEX
    Explanations

    following a

    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_22/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
     was
    -2.23
     has
    -2.13
    <h3>
    -1.93
    سبة
    -1.86
    もあります
    -1.77
    </h1>
    -1.75
     can
    -1.66
    oprecip
    -1.60
     had
    -1.59
     цену
    -1.58
    POSITIVE LOGITS
     the
    3.41
     a
    2.28
    谖
    2.14
    本日の
    2.02
     moradores
    1.95
     famílias
    1.93
     mães
    1.93
    鹩
    1.92
    獃
    1.84
    の種類
    1.83
    Activations Density 0.022%

    No Known Activations