© 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. 62823
    Prev
    Next
    INDEX
    Explanations

    review, pictures, convergence, Berlin, stains, is, across

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

    automating tasks or responses

    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
    ו
    0.54
    他
    0.53
     він
    0.51
    و
    0.50
    他的
    0.46
    ологі
    0.45
    рев
    0.45
    okon
    0.45
    你
    0.44
     Wohnung
    0.43
    POSITIVE LOGITS
    ↵
    0.55
     この
    0.50
    นี้
    0.48
    ですね
    0.48
    や
    0.47
     पिक
    0.47
     これ
    0.46
     ಸಮಸ್ಯೆ
    0.46
    癬
    0.46
     simple
    0.45
    Activations Density 0.000%

    No Known Activations