© 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. 80942
    Prev
    Next
    INDEX
    Explanations

    project statements

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

    discussing pros

    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
    сл
    0.57
     கட்டடக்கலை
    0.56
    ார்
    0.53
    миз
    0.49
    ა
    0.49
     கை
    0.48
    сков
    0.47
    органи
    0.47
    嬛
    0.47
    בוה
    0.46
    POSITIVE LOGITS
    i
    0.47
     tofu
    0.46
    print
    0.45
     SEO
    0.45
     Eq
    0.45
    ของผู้
    0.44
     l
    0.43
     Pepsi
    0.43
    lub
    0.42
    day
    0.42
    Activations Density 0.002%

    No Known Activations