© 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. 31-GEMMASCOPE-2-RES-262K
    7. 47812
    Prev
    Next
    INDEX
    Explanations

    **

    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/layer_31_width_262k_l0_medium
    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
     Traff
    0.50
    📓
    0.45
     bezig
    0.44
    萆
    0.44
    Linked
    0.43
     перспек
    0.42
     HTMLSc
    0.42
    ⛽
    0.42
     Wire
    0.41
    itabbo
    0.41
    POSITIVE LOGITS
    աս
    0.45
     a
    0.44
     decompression
    0.43
     horse
    0.43
     weight
    0.43
     typical
    0.42
    риа
    0.42
     transduction
    0.42
    ROUTE
    0.41
    胺
    0.41
    Activations Density 0.004%

    No Known Activations