© 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. 93608
    Prev
    Next
    INDEX
    Explanations

    code keywords

    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
    مار
    -0.74
    渓
    -0.74
    #[
    -0.73
    ฬ
    -0.71
    nov
    -0.71
     cero
    -0.70
    rieron
    -0.70
     Action
    -0.69
     sella
    -0.69
    格式
    -0.69
    POSITIVE LOGITS
    fuse
    0.74
     froze
    0.69
     agradecer
    0.68
    ierra
    0.68
     chắn
    0.65
     continúa
    0.64
    úcar
    0.63
    jazd
    0.63
    还会
    0.63
    NIE
    0.63
    Activations Density 0.043%

    No Known Activations