© 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. 14905
    Prev
    Next
    INDEX
    Explanations

    style, while, have, need

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

    entity and its description

    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
     pâle
    0.49
     allgemeinen
    0.48
    imetry
    0.47
    getRedTeam
    0.47
    䇝
    0.47
    磴
    0.47
    ലോക
    0.46
    烬
    0.46
    ;'>
    0.46
    gleichen
    0.45
    POSITIVE LOGITS
     Германия
    0.47
     सीनियर
    0.46
     जिम्मेदारी
    0.46
     NEA
    0.46
     टेक्निकल
    0.45
     කියලා
    0.45
    িন্দু
    0.45
     یقین
    0.42
     biking
    0.42
     фигуры
    0.42
    Activations Density 0.000%

    No Known Activations