© 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. 23717
    Prev
    Next
    INDEX
    Explanations

    technical embodiments

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

    computer name, metaphysical principles, bird

    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
    ∧
    0.43
     மத்தியில்
    0.42
     Tattha
    0.42
     crock
    0.41
     tantamount
    0.41
     Purnama
    0.41
    🚻
    0.40
    importanza
    0.40
     வித்திய
    0.40
     ಏಕೆಂದರೆ
    0.40
    POSITIVE LOGITS
    2
    0.48
    প্রাণ
    0.42
     engagements
    0.38
    ברים
    0.38
     الاجتما
    0.38
     propres
    0.37
     engagement
    0.37
     février
    0.37
     vicepresidente
    0.37
    Price
    0.37
    Activations Density 0.000%

    No Known Activations