© 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. 53628
    Prev
    Next
    INDEX
    Explanations

    terms of trust

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

    specific words followed by other words

    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
     (
    0.52
     ("
    0.49
     "...
    0.48
     («
    0.48
     কোন্‌
    0.47
     “(
    0.47
     (+
    0.46
     "(
    0.46
     "..
    0.46
     يُ
    0.46
    POSITIVE LOGITS
     ähm
    0.79
     보면은
    0.60
    you
    0.60
    ้ํา
    0.59
     Mhm
    0.57
    hashtag
    0.55
    
    0.55
     えっと
    0.53
     sogenannten
    0.52
    比如说
    0.52
    Activations Density 0.082%

    No Known Activations