© 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. 178111
    Prev
    Next
    INDEX
    Explanations

    gossip and web

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

    specific topics followed by descriptive words

    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
     marqu
    0.60
     निल
    0.50
     prosent
    0.49
    Blu
    0.49
    窯
    0.48
     Blu
    0.48
     blu
    0.47
     Blanch
    0.47
     quart
    0.46
     oyster
    0.46
    POSITIVE LOGITS
    atypes
    0.50
     impedances
    0.50
     Readiness
    0.46
     Assumptions
    0.43
     簡単
    0.43
     거고
    0.43
    践
    0.43
    dynamics
    0.43
     predictors
    0.42
     Characteristics
    0.42
    Activations Density 0.001%

    No Known Activations