© 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. 189755
    Prev
    Next
    INDEX
    Explanations

    best practices and interests

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

    ADE, ENE, inadvisable

    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
    این
    0.51
     วั
    0.49
    ک
    0.49
     رنگ
    0.47
    بی
    0.47
    みると
    0.47
     शास्त्रों
    0.46
    Ꮘ
    0.46
    بین
    0.45
     Вя
    0.44
    POSITIVE LOGITS
    ADE
    0.57
     জ্বাল
    0.48
    adrenaline
    0.47
    ATORY
    0.47
    DAY
    0.46
    KEN
    0.45
    MIN
    0.45
    usky
    0.45
    ade
    0.45
    IMG
    0.44
    Activations Density 0.001%

    No Known Activations