© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169139
    Prev
    Next
    INDEX
    Explanations

    administrative or political terms

    np_acts-logits-general · gemini-2.5-flash-lite

    lists of components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ，
    0.53
     착
    0.46
    supplied
    0.44
    （
    0.42
    śnie
    0.41
    ッグ
    0.41
    ４
    0.41
    SpriteCollision
    0.41
    Ｃ
    0.40
     bardziej
    0.40
    POSITIVE LOGITS
     Saleh
    0.52
     hoặc
    0.47
     અથવા
    0.46
     அல்லது
    0.46
     veya
    0.46
     sekal
    0.45
    หรือ
    0.44
     లేదా
    0.44
     인증
    0.44
     Telangana
    0.43
    Activations Density 0.001%

    No Known Activations