© 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. 16831
    Prev
    Next
    INDEX
    Explanations

    logging and tags

    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
    FormsModule
    0.55
    ،
    0.54
    P
    0.52
    鸰
    0.52
    パラ
    0.52
    উদাহরণ
    0.51
    PopupWindowStyle
    0.50
    䐂
    0.50
     церковь
    0.49
    cknow
    0.49
    POSITIVE LOGITS
    imilar
    0.56
     spelt
    0.55
     crested
    0.54
     en
    0.52
    en
    0.52
     nemo
    0.52
     negó
    0.51
    es
    0.51
     festgestellt
    0.51
     spectators
    0.50
    Activations Density 0.003%

    No Known Activations