© 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. 228639
    Prev
    Next
    INDEX
    Explanations

    mom running, usb port

    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
     бонусы
    0.48
     किलो
    0.48
    ाने
    0.48
     неу
    0.47
    oy
    0.47
     воен
    0.47
    %}
    0.46
    '
    0.46
     помощь
    0.46
     fomentar
    0.46
    POSITIVE LOGITS
    ἑ
    0.47
    کن
    0.44
    کم
    0.44
    ధ
    0.44
    ቆዳ
    0.44
    Sk
    0.43
    ક્ષ
    0.43
    いています
    0.43
    ୈ
    0.43
    പ്പെടുന്നു
    0.43
    Activations Density 0.000%

    No Known Activations