© 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. 32207
    Prev
    Next
    INDEX
    Explanations

    provides tutorials and code snippets

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

    code examples and declarations

    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
    Ⓡ
    0.54
    ‍♀️
    0.45
    挑戦
    0.42
     በፊት
    0.42
     Ausstattung
    0.41
     당신
    0.41
    覚えて
    0.41
     Favourite
    0.40
    网红
    0.40
     elő
    0.39
    POSITIVE LOGITS
     ['*.
    0.49
    inp
    0.44
    isDirectory
    0.41
    Funcion
    0.41
    လိုအပ်
    0.41
     dir
    0.41
     त्यावर
    0.41
    lookandfeel
    0.41
    RuL
    0.40
    不錯
    0.40
    Activations Density 0.001%

    No Known Activations