© 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. 198063
    Prev
    Next
    INDEX
    Explanations

    visiting or supporters

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

    technical configurations and explanations

    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
    કર્
    0.49
     پاسخ
    0.46
    िनल
    0.46
    utia
    0.45
    ಸೆ
    0.45
     ตอบ
    0.45
     dares
    0.44
    옵
    0.44
    खा
    0.43
     casos
    0.43
    POSITIVE LOGITS
    脸
    0.50
    裁剪
    0.48
    火
    0.45
     Duch
    0.44
    圜
    0.43
     willen
    0.42
     Duck
    0.41
     chh
    0.41
     ESTATE
    0.41
     Willoughby
    0.41
    Activations Density 0.000%

    No Known Activations