© 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. 237655
    Prev
    Next
    INDEX
    Explanations

    team regardless

    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
    টু
    0.45
    仅
    0.45
    adien
    0.45
    h
    0.44
    چنین
    0.44
    前
    0.44
    ϊ
    0.44
    x
    0.43
    ad
    0.42
    充满
    0.42
    POSITIVE LOGITS
     lám
    0.57
     নদ
    0.56
     comandos
    0.51
     योर
    0.50
     ގ
    0.49
     snowman
    0.49
     RIA
    0.48
     siebie
    0.48
    BSITE
    0.48
    링크
    0.46
    Activations Density 0.001%

    No Known Activations