© 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. 95592
    Prev
    Next
    INDEX
    Explanations

    locations, descriptions, or quantities

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

    asking for input or defining properties

    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
    cend
    0.45
    आगे
    0.45
    лд
    0.42
    enumi
    0.42
    ум
    0.41
    탯
    0.41
    cpy
    0.41
    нови
    0.40
    ৩
    0.40
    Zum
    0.39
    POSITIVE LOGITS
     SUVs
    0.52
     উপকরণ
    0.51
     profundamente
    0.51
     obe
    0.50
     சிறிய
    0.50
     বিদেশে
    0.50
     druž
    0.49
     feminists
    0.49
     igra
    0.48
     pequeña
    0.48
    Activations Density 0.000%

    No Known Activations