© 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. 14843
    Prev
    Next
    INDEX
    Explanations

    words like "only" or "this"

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

    poppy seed, permissive users, unauthorized devices

    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
     cambio
    0.48
    rik
    0.46
    oble
    0.44
     mitad
    0.43
    अ
    0.42
    stil
    0.41
     schimb
    0.41
    reb
    0.41
    o
    0.40
    Ug
    0.40
    POSITIVE LOGITS
     αυτή
    0.60
     αυτό
    0.54
     này
    0.53
     chỉ
    0.53
    只会
    0.52
     ONLY
    0.52
     yalnızca
    0.51
     এই
    0.50
     Only
    0.50
     Chỉ
    0.50
    Activations Density 0.000%

    No Known Activations