© 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. 517
    Prev
    Next
    INDEX
    Explanations

    van prefix names

    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
    経過
    -0.87
     लाग
    -0.81
     metaphysical
    -0.79
    ʎ
    -0.79
    cides
    -0.77
     personable
    -0.76
     conex
    -0.76
     exemplary
    -0.75
     vara
    -0.75
     termine
    -0.75
    POSITIVE LOGITS
    lında
    0.75
     babies
    0.73
     Babies
    0.73
    ModelMap
    0.72
    gefügt
    0.71
    duff
    0.70
    надцать
    0.69
    ListComponent
    0.67
    égalité
    0.67
     Happen
    0.67
    Activations Density 0.014%

    No Known Activations