© 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. 247408
    Prev
    Next
    INDEX
    Explanations

    created prints

    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
    穩定
    0.44
     تیل
    0.43
    ті
    0.43
     総
    0.41
     様
    0.41
     ലൈ
    0.41
     conteudo
    0.40
    矇
    0.40
     січня
    0.39
    བ་
    0.39
    POSITIVE LOGITS
     AUX
    0.50
     IPs
    0.49
    酉
    0.47
     वान
    0.47
     Apo
    0.47
     bioge
    0.46
     wsp
    0.46
    지역
    0.46
    andır
    0.46
     delimited
    0.46
    Activations Density 0.000%

    No Known Activations