© 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. 89322
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

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

    equations and numbers

    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
     D
    0.38
     N
    0.38
     S
    0.37
     sp
    0.37
     perox
    0.37
     विस्तारित
    0.37
     H
    0.37
     payday
    0.37
     Somali
    0.36
     F
    0.36
    POSITIVE LOGITS
    tting
    0.47
    வர்கள்
    0.45
    achery
    0.42
     uglify
    0.41
    naire
    0.40
    、「
    0.40
     افراد
    0.40
    gies
    0.39
     카드
    0.39
    uiswing
    0.39
    Activations Density 0.000%

    No Known Activations