© 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. 116982
    Prev
    Next
    INDEX
    Explanations

    your components pearls layouts sight

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

    specific words after punctuation

    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
     రూప
    0.54
    Catagory
    0.49
     мать
    0.49
    ActionBar
    0.48
    Bitmap
    0.48
     બની
    0.47
     設計
    0.47
     ข
    0.47
     ByteBuffer
    0.46
    Handler
    0.46
    POSITIVE LOGITS
     reveals
    0.54
     mouths
    0.52
     chants
    0.52
     socials
    0.52
     atom
    0.51
     cells
    0.48
     chy
    0.48
     temer
    0.48
     hy
    0.48
     intersected
    0.48
    Activations Density 0.000%

    No Known Activations