© 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. 88865
    Prev
    Next
    INDEX
    Explanations

    unit test descriptive blocks

    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
    (
    0.64
    iro
    0.56
    '
    0.54
    ees
    0.53
    ON
    0.52
    一樣
    0.52
    現地
    0.52
    arele
    0.52
    一些
    0.52
    iat
    0.51
    POSITIVE LOGITS
    힙
    0.59
     Technische
    0.55
    лу
    0.55
     Confira
    0.54
    с
    0.54
     confided
    0.53
    품
    0.53
    ጢ
    0.53
     commutator
    0.52
    Moto
    0.52
    Activations Density 0.001%

    No Known Activations