© 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. 86349
    Prev
    Next
    INDEX
    Explanations

    floss tape or more sheets

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

    Google Search, cloning, You can

    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
    os
    0.58
    y
    0.50
    t
    0.45
    OS
    0.45
     dados
    0.45
    ic
    0.44
     постра
    0.44
    ré
    0.43
     دیگر
    0.43
    copter
    0.43
    POSITIVE LOGITS
     ډول
    0.51
    엌
    0.47
    顾
    0.47
    顧
    0.47
     embryonic
    0.45
    뽑
    0.45
    會在
    0.44
     greenish
    0.44
    काळ
    0.44
    峴
    0.43
    Activations Density 0.000%

    No Known Activations