© 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. 6581
    Prev
    Next
    INDEX
    Explanations

    web addresses and file paths

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

    python imports

    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
    fNil
    0.24
     suppuration
    0.24
    MatContext
    0.23
     parvenir
    0.23
     забруд
    0.23
     Calyce
    0.23
     viande
    0.23
    섦
    0.22
     når
    0.22
     vanwege
    0.22
    POSITIVE LOGITS
     T
    0.30
     M
    0.30
     C
    0.29
     G
    0.29
     R
    0.28
     P
    0.26
     F
    0.26
     H
    0.26
     B
    0.25
     D
    0.25
    Activations Density 0.052%

    No Known Activations