© 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. 34-GEMMASCOPE-RES-131K
    4. 90094
    Prev
    Next
    INDEX
    Explanations

    names, kinship terms, groups

    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_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
     and
    -2.22
     of
    -1.38
    }}$
    -1.33
    )];
    
    -1.18
    OCCURRED
    -1.16
     him
    -1.13
    >(</
    -1.11
    お待ちしております
    -1.10
    Опис
    -1.09
    PENDAHULUAN
    -1.09
    POSITIVE LOGITS
     you
    2.91
    ,
    2.73
     please
    2.05
     your
    1.92
     what
    1.87
     why
    1.63
    ،
    1.55
     should
    1.50
     those
    1.45
     Oliven
    1.38
    Activations Density 0.022%

    No Known Activations