© 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. 193809
    Prev
    Next
    INDEX
    Explanations

    viewing

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

    selling with minimal upfront inventory

    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
    Israel
    0.45
    ণিত
    0.44
     удосто
    0.43
    केश
    0.43
    ঘ্র
    0.42
    StateHandler
    0.42
     종합
    0.41
    a
    0.41
     Oder
    0.40
    Kenya
    0.40
    POSITIVE LOGITS
    からの
    0.45
    はない
    0.45
    썹
    0.45
    がなく
    0.43
     MACHIN
    0.43
     fixe
    0.43
     gua
    0.43
     αὐ
    0.42
     ঘে
    0.42
    を変
    0.41
    Activations Density 0.002%

    No Known Activations