© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7475
    Prev
    Next
    INDEX
    Explanations

    little over

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

    common function words and categories

    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
    am
    0.58
    ↵
    0.52
    Help
    0.52
    TikTok
    0.52
    OK
    0.51
    Video
    0.51
    father
    0.50
    bri
    0.50
    Department
    0.49
    i
    0.49
    POSITIVE LOGITS
    捛
    0.57
    喡
    0.55
     ~\
    0.52
     delineate
    0.51
     !",
    0.50
    綸
    0.50
    簷
    0.50
    褴
    0.50
    。",
    0.50
    殞
    0.50
    Activations Density 0.000%

    No Known Activations