© 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. 77256
    Prev
    Next
    INDEX
    Explanations

    names ending in po or preceded by identifier

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

    attribute labels or specifications

    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
    흠
    0.39
    Productions
    0.39
     سایر
    0.38
    레
    0.37
     পারেনি
    0.37
    俱乐
    0.35
    Combat
    0.35
    崔
    0.35
    Além
    0.35
     대신
    0.35
    POSITIVE LOGITS
     thereof
    0.42
     Yara
    0.41
     disso
    0.39
     Bong
    0.39
     Sock
    0.39
     Kidman
    0.39
     Even
    0.38
     Tomato
    0.38
     variant
    0.38
     corollary
    0.38
    Activations Density 0.111%

    No Known Activations