© 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. 145683
    Prev
    Next
    INDEX
    Explanations

    slide, transaction, played

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

    Guard Blocks

    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
    PORT
    0.45
    UPDATE
    0.43
    ا
    0.41
    you
    0.41
     slap
    0.41
    update
    0.41
     HStack
    0.40
     sprawd
    0.40
    usammen
    0.40
     sagen
    0.40
    POSITIVE LOGITS
     Ευ
    0.49
    以后
    0.46
    ጀት
    0.45
    χρι
    0.44
    馥
    0.44
    ಿಸುವ
    0.43
    атра
    0.43
    Parrocchia
    0.43
     próprios
    0.43
    之后
    0.42
    Activations Density 0.002%

    No Known Activations