© 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. 857
    Prev
    Next
    INDEX
    Explanations

    following `the` or `of`

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

    explaining options, concepts, or prompts

    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
    れている
    0.48
    臺灣
    0.46
    だ
    0.46
    韜
    0.45
    ágina
    0.45
     tempData
    0.44
    ]<<
    0.43
    内の
    0.43
     ప్రజా
    0.42
     melhor
    0.42
    POSITIVE LOGITS
    ویز
    0.51
    önes
    0.50
     Kiz
    0.49
    ۔
    0.49
    ف
    0.48
    ments
    0.48
     Sonne
    0.47
    isms
    0.46
     Oto
    0.46
    otel
    0.46
    Activations Density 0.000%

    No Known Activations