© 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. 121286
    Prev
    Next
    INDEX
    Explanations

    cost or rest

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

    specifications of features and lists

    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
    瑩
    0.47
    ol
    0.42
    getText
    0.42
    換
    0.41
    ib
    0.41
    getVideo
    0.40
    他也
    0.40
    歸
    0.40
     getVideo
    0.39
    ar
    0.39
    POSITIVE LOGITS
     podczas
    0.50
     اولین
    0.50
     élu
    0.50
     Rye
    0.49
     высоким
    0.49
     świą
    0.49
    !।
    0.48
     alcun
    0.48
    いっぱい
    0.48
     العديد
    0.47
    Activations Density 0.000%

    No Known Activations