© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12567
    Prev
    Next
    INDEX
    Explanations

    Final answers in boxes

    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/layer_40_width_262k_l0_medium
    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
    ć
    0.42
    so
    0.41
    ,
    0.38
    …
    0.34
    je
    0.34
     நா
    0.33
     (!)
    0.33
    spor
    0.32
    nač
    0.32
    (!)
    0.32
    POSITIVE LOGITS
    =========
    0.34
    
    0.34
     Nonlinear
    0.34
    FBSDKApp
    0.33
     Baiklah
    0.33
     nameWithOwner
    0.33
     Graphical
    0.33
     svůj
    0.33
     Utilizing
    0.32
     Pursuant
    0.32
    Activations Density 0.037%

    No Known Activations