© 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. 11359
    Prev
    Next
    INDEX
    Explanations

    100% or full states

    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
    skraft
    0.46
     मोठ्या
    0.45
     ৩
    0.45
     *,
    0.44
     수를
    0.44
     около
    0.44
    \}.
    0.43
    
    0.43
    ಳ್ಳ
    0.43
    overleftarrow
    0.43
    POSITIVE LOGITS
     percent
    0.71
     Zero
    0.64
     zero
    0.63
     perfetto
    0.61
     ZERO
    0.59
     Percent
    0.57
     percents
    0.57
     Fully
    0.56
     perfeito
    0.55
     zéro
    0.55
    Activations Density 0.037%

    No Known Activations