© 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. 143547
    Prev
    Next
    INDEX
    Explanations

    taxes due, may try

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

    Cat Pose, Remember everyone, sequence of

    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
     способом
    0.51
    
    0.48
     grievous
    0.48
    Imidazole
    0.45
     компонентов
    0.45
    Geography
    0.43
    ៕
    0.43
     اعرف
    0.43
     enshr
    0.43
     инде
    0.42
    POSITIVE LOGITS
    나
    0.52
    バー
    0.48
    στ
    0.47
     sections
    0.47
     साढ़े
    0.47
    ש
    0.47
    প্রায়
    0.46
    라
    0.46
    駆け
    0.46
    す
    0.46
    Activations Density 0.001%

    No Known Activations