© 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. 25940
    Prev
    Next
    INDEX
    Explanations

    artificial materials, creations, or fraudulent items

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

    FV, compatibility, robust, initiate

    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
    BackgroundHelper
    0.43
     nisi
    0.43
     geralmente
    0.40
     siang
    0.40
     flera
    0.40
    掄
    0.40
     armes
    0.39
     Congress
    0.39
     bello
    0.38
    䛶
    0.38
    POSITIVE LOGITS
    რც
    0.44
    яд
    0.44
    カリ
    0.44
    近期
    0.43
    calf
    0.43
     nanow
    0.43
    gada
    0.43
    حث
    0.42
     Elovl
    0.42
    urança
    0.42
    Activations Density 0.000%

    No Known Activations