© 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. 57551
    Prev
    Next
    INDEX
    Explanations

    fall edition

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

    value creation

    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
     اسئله
    0.51
    [,-
    0.45
     hearers
    0.45
     lube
    0.44
     groaned
    0.43
    ｿ
    0.42
     localize
    0.42
     wither
    0.42
     merkle
    0.42
     socialists
    0.42
    POSITIVE LOGITS
     Rental
    0.49
     Lebih
    0.46
    Experimental
    0.44
    覦
    0.44
     İ
    0.44
     menjalani
    0.43
     Regulation
    0.43
     İş
    0.43
    孱
    0.43
    勍
    0.43
    Activations Density 0.000%

    No Known Activations