© 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. 66441
    Prev
    Next
    INDEX
    Explanations

    whether introducing alternatives

    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
     хорошо
    -1.57
     收納
    -1.44
     atmosfera
    -1.41
     花卉
    -1.36
     unu
    -1.34
     seraient
    -1.32
     素描
    -1.30
    nicy
    -1.29
    了一个
    -1.28
     pez
    -1.28
    POSITIVE LOGITS
     it
    2.30
     It
    1.80
     from
    1.69
     Whether
    1.66
     They
    1.65
     they
    1.59
    for
    1.55
    from
    1.52
     you
    1.49
     Their
    1.38
    Activations Density 0.007%

    No Known Activations