© 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. 223337
    Prev
    Next
    INDEX
    Explanations

    below

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

    words of wisdom entering networks

    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
    桂
    0.53
    ेंगू
    0.52
    ल्क
    0.50
    Ꭳ
    0.49
    馊
    0.47
     Тыва
    0.47
     forcing
    0.46
     Arran
    0.46
    }"]
    0.46
     interfer
    0.45
    POSITIVE LOGITS
     Fläche
    0.48
    headed
    0.46
    nea
    0.45
     materially
    0.45
    emia
    0.45
    ocene
    0.44
    akun
    0.44
    '
    0.44
    ’
    0.43
     verstehen
    0.43
    Activations Density 0.000%

    No Known Activations