© 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. 81112
    Prev
    Next
    INDEX
    Explanations

    often overlaps or combines

    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
     आत्मा
    0.54
     სტ
    0.54
     מק
    0.47
    <unused2180>
    0.47
    DeleteDialogOpen
    0.46
     deme
    0.46
     ז
    0.45
     Ingrid
    0.45
    ング
    0.45
     человек
    0.45
    POSITIVE LOGITS
    c
    0.48
    wait
    0.43
    as
    0.42
    Bio
    0.42
    endedor
    0.41
    rio
    0.40
    Force
    0.40
    Aqua
    0.40
    Nord
    0.40
    AMT
    0.39
    Activations Density 0.004%

    No Known Activations