© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203127
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases or identification

    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
    kovskij
    0.50
    ကိုယ်
    0.50
    uido
    0.50
     那麼
    0.48
    <0xB3>
    0.47
    ರ್ಶ
    0.47
    DIFF
    0.47
    salaryfrom
    0.47
    絟
    0.47
    ول
    0.46
    POSITIVE LOGITS
    At
    0.59
    Band
    0.50
    Kn
    0.48
     At
    0.48
    Fraud
    0.47
    Garden
    0.47
    </i>
    0.46
     Band
    0.46
    К
    0.46
    Bedroom
    0.46
    Activations Density 0.000%

    No Known Activations