© 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. 202082
    Prev
    Next
    INDEX
    Explanations

    password resets

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

    ggml ai model format

    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
     میلیون
    0.45
     刺繍
    0.45
    𝗡
    0.42
     ไว้
    0.42
    த்
    0.42
    ยก
    0.41
    を除く
    0.41
     দৈ
    0.40
     этих
    0.40
     EI
    0.40
    POSITIVE LOGITS
     Words
    0.45
    Words
    0.44
    c
    0.43
     Feather
    0.43
    incub
    0.43
    curr
    0.42
    faceted
    0.42
     Pediatr
    0.42
    uddled
    0.42
    started
    0.42
    Activations Density 0.001%

    No Known Activations