© 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. 79094
    Prev
    Next
    INDEX
    Explanations

    Volcano Cottages

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

    monitoring logging

    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
     pelos
    0.50
     ڈپ
    0.49
     stimulated
    0.47
    츰
    0.47
    stimulated
    0.46
    perl
    0.46
     DST
    0.45
     Departament
    0.45
     نوجوان
    0.44
    ⑸
    0.44
    POSITIVE LOGITS
    ล
    0.49
    älle
    0.48
     fok
    0.47
    झ
    0.46
     calculators
    0.45
     afe
    0.45
     calculator
    0.45
     sok
    0.44
     information
    0.44
     tahan
    0.44
    Activations Density 0.001%

    No Known Activations