© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1845
    Prev
    Next
    INDEX
    Explanations

    there's no

    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_65k_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
    racting
    0.30
    ？
    0.28
     Todos
    0.27
    ;
    0.27
     mesmos
    0.27
    todos
    0.26
     Wherever
    0.26
     Whether
    0.26
     všechny
    0.26
    指的是
    0.26
    POSITIVE LOGITS
     plenty
    0.60
     no
    0.46
     reason
    0.45
     a
    0.42
     uncertainty
    0.41
     considerable
    0.40
     ample
    0.40
     disagreement
    0.37
     consensus
    0.37
     confusion
    0.37
    Activations Density 0.343%

    No Known Activations