© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40435
    Prev
    Next
    INDEX
    Explanations

    camera, dual, curios, tax-deductible

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

    tasks, diaspora, than

    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
    கோ
    0.44
    ĥ
    0.42
    or
    0.40
    img
    0.39
    tor
    0.39
    
    0.38
    array
    0.38
     வடக்கு
    0.38
     Summers
    0.38
    Ī
    0.38
    POSITIVE LOGITS
    掊
    0.46
    动的
    0.46
     상담
    0.42
    просы
    0.42
     pedibus
    0.42
    ữu
    0.40
     intéressant
    0.40
    新闻
    0.39
     познакоми
    0.39
    toBeTruthy
    0.39
    Activations Density 0.000%

    No Known Activations