© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99178
    Prev
    Next
    INDEX
    Explanations

    company names and collections

    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
    clutch
    -0.80
    Մ
    -0.76
    Sid
    -0.74
    احت
    -0.71
    above
    -0.70
    الق
    -0.69
     Withdrawal
    -0.69
    Լ
    -0.68
    गु
    -0.68
    isdigit
    -0.68
    POSITIVE LOGITS
    Xar
    0.79
     урна
    0.77
    rix
    0.74
    Aza
    0.71
     rebuilt
    0.69
    Engl
    0.69
    殊
    0.68
    何况
    0.68
     स्था
    0.67
     Rowe
    0.67
    Activations Density 0.042%

    No Known Activations