© 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. 51831
    Prev
    Next
    INDEX
    Explanations

    version of , plan to , society of

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

    directory or code commands

    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
     correspondence
    0.47
     impug
    0.44
     dysfunctional
    0.44
     cluttered
    0.44
    무
    0.43
    𝗙
    0.43
     impairments
    0.43
    ಉ
    0.42
    Ձ
    0.42
     Inspirational
    0.41
    POSITIVE LOGITS
    Lm
    0.53
    
    0.49
    xlab
    0.46
    UIKit
    0.46
    jsonplaceholder
    0.46
    Lk
    0.46
    Hc
    0.45
     到
    0.44
    çou
    0.43
     justamente
    0.43
    Activations Density 0.000%

    No Known Activations