© 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. 70042
    Prev
    Next
    INDEX
    Explanations

    boost namespace qualifiers

    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
    wachsen
    -0.85
    Fou
    -0.79
    Virtual
    -0.73
    ешь
    -0.69
    Value
    -0.69
     Value
    -0.68
     Virtual
    -0.68
    PENG
    -0.68
    няття
    -0.67
    涉及
    -0.66
    POSITIVE LOGITS
     εφ
    0.73
    ヒール
    0.70
    Folks
    0.69
    orso
    0.66
     nastav
    0.65
     syringe
    0.65
    erano
    0.65
    僱
    0.64
     Ihnen
    0.64
     Tailor
    0.64
    Activations Density 0.046%

    No Known Activations