© 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. 188428
    Prev
    Next
    INDEX
    Explanations

    more over

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

    electrolysis or manipulation

    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
    リーダー
    0.51
    教學
    0.45
    പേക്ഷ
    0.45
    зулта
    0.45
     SERVER
    0.44
     Utilizamos
    0.44
    䡆
    0.44
    ोने
    0.44
    мещение
    0.43
     médioc
    0.43
    POSITIVE LOGITS
    bn
    0.43
     expansive
    0.42
    boolProp
    0.41
     lysed
    0.41
     />
    0.41
    tage
    0.41
    cV
    0.40
    zd
    0.40
    yl
    0.40
     overshadow
    0.40
    Activations Density 0.002%

    No Known Activations