© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63789
    Prev
    Next
    INDEX
    Explanations

    software licensing and code

    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
     inhoud
    -0.80
     '@/
    -0.68
    miec
    -0.67
    chandising
    -0.65
     ゆ
    -0.64
    lería
    -0.64
     asym
    -0.63
     Vatican
    -0.63
    руп
    -0.62
    arky
    -0.62
    POSITIVE LOGITS
    ﹞
    0.71
     UPPER
    0.71
    DHL
    0.70
    textAlign
    0.67
     Ral
    0.66
     Daun
    0.66
     ポケモン
    0.65
    ︶
    0.65
     align
    0.65
    AppendLine
    0.65
    Activations Density 0.097%

    No Known Activations