© 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. 34466
    Prev
    Next
    INDEX
    Explanations

    location or identifier

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

    deep learning models

    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
    コ
    0.52
     Ram
    0.50
     naps
    0.49
     dispers
    0.46
    ব
    0.46
    ش
    0.45
     ناج
    0.45
    ドー
    0.45
     аэро
    0.44
     ‏
    0.44
    POSITIVE LOGITS
    नेशन
    0.49
    feet
    0.48
    iby
    0.48
    spro
    0.47
    ourcen
    0.47
    wait
    0.47
    ikey
    0.47
    skilled
    0.46
    provoking
    0.45
    里程
    0.45
    Activations Density 0.000%

    No Known Activations