© 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. 34-GEMMASCOPE-RES-131K
    7. 58814
    Prev
    Next
    INDEX
    Explanations

    that doesn't

    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
     می‌کن
    -0.94
     getC
    -0.85
     بوده
    -0.82
    zysz
    -0.81
    вропей
    -0.79
    ')}}">
    -0.77
     Cf
    -0.77
    weza
    -0.76
    ()]);
    -0.74
    []=$
    -0.74
    POSITIVE LOGITS
     doesn
    4.06
     does
    3.59
    doesn
    2.67
    Doesn
    2.63
    Does
    2.55
     doesnt
    2.53
     Doesn
    2.52
     DOES
    2.52
    并不
    2.52
    does
    2.52
    Activations Density 0.041%

    No Known Activations