© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75135
    Prev
    Next
    INDEX
    Explanations

    how to / questions

    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
     egenskaper
    -1.13
     jPanel
    -1.08
    isinin
    -1.05
     л
    -1.03
     février
    -1.02
    ಈ
    -1.02
     junho
    -1.01
    lista
    -1.01
     guste
    -1.01
     BOOL
    -0.99
    POSITIVE LOGITS
    </h2>
    1.32
     移動
    1.24
     and
    1.12
    2
    1.02
     who
    1.02
    CIUDAD
    0.98
    toolStrip
    0.97
    ”.
    0.96
    可能有
    0.96
     responsáveis
    0.95
    Activations Density 0.000%

    No Known Activations