© 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. 239635
    Prev
    Next
    INDEX
    Explanations

    marks centurygroup sheetsshout out

    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
    𒂍
    0.66
    lefthar
    0.56
    Ⴖ
    0.54
     インド
    0.54
     eşit
    0.54
     미술
    0.54
     incremento
    0.53
     ステン
    0.53
    scriptsize
    0.53
    umum
    0.52
    POSITIVE LOGITS
     leave
    0.49
    拜
    0.48
     Lane
    0.47
    <0xE3>
    0.46
     distribution
    0.46
    기
    0.46
     safeguard
    0.46
     lane
    0.45
     press
    0.44
     arm
    0.44
    Activations Density 0.000%

    No Known Activations