© 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. 201449
    Prev
    Next
    INDEX
    Explanations

    children, son, aunt

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

    analyzing doping profiles

    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
    的首
    0.52
     geared
    0.50
     clandestine
    0.50
     taint
    0.49
    р
    0.48
     Maloney
    0.46
     swinging
    0.46
     mainstay
    0.46
     dependency
    0.46
     larc
    0.46
    POSITIVE LOGITS
    }*/
    0.52
     সন্তানদের
    0.49
    ρων
    0.48
     ಮಕ್ಕ
    0.46
    ſon
    0.46
    Ἱ
    0.46
     καλύτε
    0.45
    λη
    0.44
     บอก
    0.44
     परंतु
    0.43
    Activations Density 0.000%

    No Known Activations