© 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. 23154
    Prev
    Next
    INDEX
    Explanations

    course decline

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

    is or are followed by a characteristic

    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
     Üniversitesi
    0.47
    உலக
    0.46
    쿡
    0.46
     kuna
    0.46
     एलो
    0.46
     Sử
    0.46
    大學
    0.45
    國際
    0.45
     開
    0.44
     就
    0.44
    POSITIVE LOGITS
    balls
    0.43
     deleterious
    0.43
     deformed
    0.43
     perturbed
    0.42
    ponding
    0.40
    ogenerated
    0.40
    khar
    0.40
     congested
    0.39
    fected
    0.38
     colloidal
    0.38
    Activations Density 0.000%

    No Known Activations