© 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. 58473
    Prev
    Next
    INDEX
    Explanations

    common sentence starters

    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
    umas
    -0.73
     Gala
    -0.73
     quies
    -0.72
     ministers
    -0.72
     carbonic
    -0.71
    琳
    -0.71
    ጤ
    -0.71
    roffene
    -0.70
     Peso
    -0.70
    الی
    -0.69
    POSITIVE LOGITS
     Come
    0.85
     candidates
    0.75
     buys
    0.75
    ళ
    0.75
     precin
    0.74
     proclaimed
    0.73
     candidatos
    0.73
     phenomena
    0.72
     positions
    0.71
    >({
    0.71
    Activations Density 0.010%

    No Known Activations