© 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. 219276
    Prev
    Next
    INDEX
    Explanations

    fortentously

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

    Key explaining definitions or principles

    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
    ))$,
    0.50
     mediante
    0.46
     स्टील
    0.46
     kaleidoscopic
    0.46
     ಉ
    0.45
    ))$.
    0.45
     billowing
    0.45
    carros
    0.45
     كأس
    0.44
    дм
    0.44
    POSITIVE LOGITS
    Ｓ
    0.46
    िश्व
    0.44
     Minerva
    0.43
    女子
    0.43
    氅
    0.43
     kont
    0.42
     Mutable
    0.42
    北方
    0.42
     amulet
    0.42
     kry
    0.41
    Activations Density 0.001%

    No Known Activations