© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 5080
    Prev
    Next
    INDEX
    Explanations

    social, translation, science, starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    valores
    0.44
    ckså
    0.40
     పుష్
    0.39
     revisited
    0.38
     kaca
    0.38
     нулю
    0.37
     꽃
    0.36
    犯
    0.36
    NodeType
    0.35
    ulosa
    0.35
    POSITIVE LOGITS
    しょ
    0.50
    parent
    0.50
    translation
    0.45
    色
    0.45
    協
    0.44
     मे
    0.43
    エ
    0.43
    ियन
    0.43
    ле
    0.42
    ப்பட
    0.41
    Activations Density 0.039%

    No Known Activations