© 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. 22-GEMMASCOPE-RES-131K
    7. 64893
    Prev
    Next
    INDEX
    Explanations

    results of competitions or leagues

    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_22/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
     nouve
    -1.25
     already
    -1.20
     уже
    -1.12
     вже
    -1.11
     neceff
    -1.07
     dopiero
    -1.05
    以便
    -1.05
     ſp
    -1.05
    mathrm
    -1.04
     another
    -1.02
    POSITIVE LOGITS
    囑
    1.21
    𓏸
    1.20
    院校
    1.18
    釐
    1.17
     during
    1.11
    录取
    1.09
    felizmente
    1.09
    cún
    1.07
     utro
    1.05
    기도
    1.04
    Activations Density 0.049%

    No Known Activations