© 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. 32633
    Prev
    Next
    INDEX
    Explanations

    application submission

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

    code, configuration, instructions

    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
    نیٹ
    0.48
    énération
    0.46
    жде
    0.45
    ющему
    0.43
    nière
    0.43
    énagement
    0.43
    Paged
    0.43
    ᖓ
    0.42
     sorption
    0.42
    лето
    0.42
    POSITIVE LOGITS
    _
    0.54
    <0x0D>
    0.50
     Vict
    0.47
     automatic
    0.46
    も
    0.46
     गए
    0.45
    +
    0.45
    ↵↵
    0.45
     Oct
    0.45
     BUT
    0.45
    Activations Density 0.000%

    No Known Activations