© 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. 73487
    Prev
    Next
    INDEX
    Explanations

    specific phrases after common words

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

    avoiding specific items or states

    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
     ché
    0.48
    \";
    0.46
     وهي
    0.46
     ឬ
    0.45
    ”;
    0.43
    ’;
    0.43
     时尚
    0.43
     océ
    0.43
     splash
    0.42
     khủng
    0.42
    POSITIVE LOGITS
    B
    0.53
    G
    0.52
    DE
    0.48
    graf
    0.47
    Pol
    0.47
     S
    0.47
    acceptance
    0.46
    Lip
    0.46
    Jenis
    0.46
    Renk
    0.46
    Activations Density 0.001%

    No Known Activations