© 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. 2874
    Prev
    Next
    INDEX
    Explanations

    Biofeedback

    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
     (
    -1.35
     становника
    -1.02
    According
    -1.02
    不是很
    -0.97
     trå
    -0.97
     др
    -0.97
    cioni
    -0.96
    Famous
    -0.92
     flesta
    -0.92
     egenskaper
    -0.91
    POSITIVE LOGITS
    ঋ
    1.13
    了些
    1.12
     prachtige
    1.12
    ṇa
    1.09
     hetzelfde
    1.07
     prachtig
    1.05
    擻
    1.05
     geweldig
    1.04
     habang
    1.03
    /#{
    1.02
    Activations Density 0.022%

    No Known Activations