© 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-262K
    7. 167447
    Prev
    Next
    INDEX
    Explanations

    theatricality, flourishes

    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
    Broad
    0.42
     See
    0.39
     Messi
    0.39
     maz
    0.38
     Broad
    0.38
     m
    0.38
     Kings
    0.38
     بالج
    0.37
     Tell
    0.36
    ϊ
    0.36
    POSITIVE LOGITS
    桨
    0.44
     кру
    0.41
    ependence
    0.41
    INER
    0.40
     पावसा
    0.40
    সল
    0.39
     রহিয়াছে
    0.39
    Bookmarks
    0.39
    ोंने
    0.39
    𐰚
    0.39
    Activations Density 0.001%

    No Known Activations