© 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. 30438
    Prev
    Next
    INDEX
    Explanations

    no right or acquire any

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

    comparisons with larger

    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
     ರ
    0.46
     ગો
    0.43
     लेनी
    0.40
    জন
    0.39
     Gim
    0.39
     ర
    0.39
     र
    0.39
    आर
    0.39
     ग्राम
    0.39
     使っ
    0.38
    POSITIVE LOGITS
    氩
    0.44
     Autres
    0.43
    ിട
    0.41
    alcool
    0.39
     bravo
    0.39
     padam
    0.39
    qualiter
    0.38
    気が
    0.38
     salari
    0.38
     unul
    0.38
    Activations Density 0.000%

    No Known Activations