© 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. 94931
    Prev
    Next
    INDEX
    Explanations

    locations or states

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

    core functionality, traditionally seen, cornerstone of

    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
    b
    0.70
     wines
    0.57
     práct
    0.54
    ת
    0.54
    ↵↵
    0.53
    k
    0.53
    u
    0.52
     to
    0.50
    M
    0.50
     you
    0.50
    POSITIVE LOGITS
     子供
    0.55
    ጥነት
    0.55
     Idha
    0.54
    厓
    0.53
     东
    0.52
    ༡
    0.52
    ഭ്യാസ
    0.49
     国産
    0.49
     டோ
    0.49
    식회사
    0.48
    Activations Density 0.000%

    No Known Activations