© 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. 101717
    Prev
    Next
    INDEX
    Explanations

    civil war pension application

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

    **"""

    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
    嶂
    0.48
    Uit
    0.47
     डिजाईन
    0.45
    স
    0.45
     Prec
    0.44
     JHEP
    0.44
    Manifest
    0.44
    鼕
    0.43
    Decor
    0.43
    Ле
    0.42
    POSITIVE LOGITS
     afterDir
    0.48
    on
    0.48
    cannot
    0.44
    as
    0.44
     {:?}",
    0.43
     coscienza
    0.42
     চাচ
    0.42
    。",
    0.41
    ”、
    0.41
    ponente
    0.41
    Activations Density 0.000%

    No Known Activations