© 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-65K
    7. 2143
    Prev
    Next
    INDEX
    Explanations

    documentation labels and code structure

    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_65k_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
     an
    0.43
    ,
    0.40
    .
    0.39
     a
    0.39
     Troubleshooting
    0.38
    ，
    0.37
    0.37
     Using
    0.35
     immunology
    0.34
     Krause
    0.34
    POSITIVE LOGITS
    К
    0.73
    на
    0.62
    ک
    0.62
    ה
    0.59
    де
    0.57
    ли
    0.54
    w
    0.54
    м
    0.54
    ه
    0.52
    P
    0.51
    Activations Density 0.485%

    No Known Activations