© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34623
    Prev
    Next
    INDEX
    Explanations

    argmax and MAP estimation

    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_16_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
    *
    0.77
     treacherous
    0.73
    -
    0.73
    rooted
    0.71
    ),
    0.70
    )*
    0.67
    )
    0.67
     hateful
    0.65
    [
    0.65
    a
    0.64
    POSITIVE LOGITS
    ש
    0.65
     figsize
    0.59
     ingresso
    0.59
     ilmiah
    0.59
    ">=
    0.58
    鳎
    0.58
     scaler
    0.57
     capacitación
    0.57
     clearContext
    0.57
     linea
    0.56
    Activations Density 0.001%

    No Known Activations