© 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. 205281
    Prev
    Next
    INDEX
    Explanations

    requires a significant

    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
    వారం
    0.52
    说
    0.50
    塩
    0.49
     स्टेशनों
    0.46
    ন
    0.46
    ंनी
    0.45
    ⵍ
    0.45
     Kreuz
    0.44
    க
    0.43
    LISTEN
    0.43
    POSITIVE LOGITS
    core
    0.50
    fulfillment
    0.49
    pect
    0.49
     delay
    0.45
    orh
    0.44
     horses
    0.44
    veh
    0.44
    cella
    0.44
    flin
    0.43
    mgmt
    0.43
    Activations Density 0.004%

    No Known Activations