© 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. 104310
    Prev
    Next
    INDEX
    Explanations

    statement of new information

    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
    髫
    -1.29
     esconder
    -1.16
    athers
    -1.10
    翃
    -1.09
    fficients
    -1.09
    )++;
    -1.07
    öhe
    -1.06
    addGap
    -1.05
    >+</
    -1.05
     conexiones
    -1.05
    POSITIVE LOGITS
     are
    2.77
     is
    2.58
     were
    1.88
    的是
    1.77
    ,
    1.76
     in
    1.70
     for
    1.48
     was
    1.38
     would
    1.23
    :
    1.23
    Activations Density 0.040%

    No Known Activations