© 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. 31866
    Prev
    Next
    INDEX
    Explanations

    instructions, technical terms, and descriptions

    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
     منك
    0.43
     પાસેથી
    0.42
     Penguin
    0.41
    ко
    0.41
     Zombie
    0.41
    ائن
    0.40
     G
    0.40
    食
    0.40
    ிலிருந்து
    0.40
     subtracted
    0.40
    POSITIVE LOGITS
     অবাধ
    0.52
    ğine
    0.52
     adequada
    0.52
    🧼
    0.50
     permitió
    0.48
    ʿ
    0.48
     nécess
    0.48
     važ
    0.47
     помогает
    0.47
    çar
    0.46
    Activations Density 0.000%

    No Known Activations