© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 65109
    Prev
    Next
    INDEX
    Explanations

    technical calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Baseline
    0.47
    Baseline
    0.44
     maestro
    0.42
     MUSE
    0.41
    appreciated
    0.41
     baseline
    0.39
     înainte
    0.39
    }:$
    0.38
     हामी
    0.38
     Bassett
    0.38
    POSITIVE LOGITS
    public
    0.40
     public
    0.35
    amish
    0.34
     Scand
    0.34
    (*
    0.33
    пка
    0.33
    ScrollBar
    0.33
    Uncle
    0.33
    ె
    0.33
    achim
    0.32
    Activations Density 0.027%

    No Known Activations