© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72597
    Prev
    Next
    INDEX
    Explanations

    would take or be

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

    WordPress, numbers, Women

    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
    賀
    0.47
     Schol
    0.43
     Predictive
    0.40
     trained
    0.40
     zeggen
    0.40
     Turnover
    0.40
     Carlson
    0.39
     Treat
    0.39
     Marian
    0.39
     Pleasant
    0.39
    POSITIVE LOGITS
    DRI
    0.43
    }\
    0.42
    émi
    0.42
     pels
    0.42
    的书
    0.42
     miembros
    0.42
    shr
    0.41
     ideally
    0.41
    כול
    0.41
     skulls
    0.41
    Activations Density 0.000%

    No Known Activations