© 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. 75076
    Prev
    Next
    INDEX
    Explanations

    experience and exploration

    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
     polin
    0.47
    nier
    0.45
    汢
    0.45
    㺪
    0.45
    unct
    0.45
     sant
    0.44
    ی
    0.44
    Cread
    0.44
    ņi
    0.44
     lorsque
    0.43
    POSITIVE LOGITS
    л
    0.45
    ancji
    0.43
    foils
    0.42
    сма
    0.42
     pills
    0.39
     discouraging
    0.39
    absch
    0.39
    veys
    0.39
     commissions
    0.38
    TableRow
    0.38
    Activations Density 0.000%

    No Known Activations