© 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. 39972
    Prev
    Next
    INDEX
    Explanations

    accepting the, approval of, causes eczema

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

    server farm

    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
    ন
    0.51
    ب
    0.49
    er
    0.47
    ousing
    0.47
    as
    0.46
    ر
    0.46
    elling
    0.45
    and
    0.44
    arm
    0.44
    ób
    0.44
    POSITIVE LOGITS
    縣
    0.48
     sytu
    0.46
     Macy
    0.45
     cityName
    0.44
     webhook
    0.43
     oggetto
    0.43
     getText
    0.43
     завдання
    0.42
     isAuthenticated
    0.41
     sytuacji
    0.41
    Activations Density 0.000%

    No Known Activations