© 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. 210834
    Prev
    Next
    INDEX
    Explanations

    focus on, secondary benefits, various drivers

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

    descriptive adjectives and explanations

    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
    К
    0.63
    Но
    0.61
    0.60
    Ле
    0.55
    Мен
    0.54
    О
    0.54
    у
    0.52
    НО
    0.52
    }\
    0.52
    بط
    0.52
    POSITIVE LOGITS
     lahko
    0.46
     segar
    0.46
     ιδια
    0.45
     tę
    0.45
    odu
    0.45
     στ
    0.45
     menambah
    0.45
     ως
    0.45
     monter
    0.45
     mempertahankan
    0.45
    Activations Density 0.001%

    No Known Activations