© 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. 100874
    Prev
    Next
    INDEX
    Explanations

    microphone, driver, birth, died

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

    within you

    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
    ur
    0.59
    is
    0.50
    ри
    0.49
    era
    0.48
    '
    0.48
    anes
    0.46
    ri
    0.46
    re
    0.45
     era
    0.44
    tu
    0.44
    POSITIVE LOGITS
     Principe
    0.58
    有點
    0.51
    的数量
    0.51
     Université
    0.50
    恽
    0.50
     bienvenue
    0.49
    תי
    0.48
    ڦ
    0.48
    RadioButton
    0.47
     QPushButton
    0.47
    Activations Density 0.001%

    No Known Activations