© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152199
    Prev
    Next
    INDEX
    Explanations

    courtesy of

    np_acts-logits-general · gemini-2.5-flash-lite

    allows organizations to focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    و
    0.57
    ки
    0.50
    、（
    0.46
    ፣
    0.46
    、
    0.46
    ،
    0.46
    *,
    0.46
     heartbreak
    0.46
     kisses
    0.45
    ش
    0.45
    POSITIVE LOGITS
     ሂደት
    0.47
    ‌است
    0.47
     문제를
    0.46
     통해
    0.45
    <unused2157>
    0.45
     작업을
    0.44
     probleme
    0.42
     ጉዳ
    0.42
     உருவாக்க
    0.42
     Constraints
    0.42
    Activations Density 0.000%

    No Known Activations