© 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. 177191
    Prev
    Next
    INDEX
    Explanations

    candy, spyware, sewage, water

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

    expected result manual

    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
    犹豫
    0.47
    ס
    0.45
    álisis
    0.45
    IDO
    0.45
    Storia
    0.45
    张
    0.44
     suprem
    0.43
    Chars
    0.43
    imbulkan
    0.43
    ườ
    0.43
    POSITIVE LOGITS
     cargo
    0.42
     бизнес
    0.42
     再
    0.42
     Phnom
    0.41
     hydraulics
    0.40
    ᱾
    0.40
     hijacked
    0.40
    沘
    0.39
    ရန်
    0.39
    スク
    0.38
    Activations Density 0.000%

    No Known Activations