© 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. 110984
    Prev
    Next
    INDEX
    Explanations

    serial monitor, alternative model, false encouragement

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

    dark humor and translation

    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
     cowboy
    0.49
    żu
    0.49
    临
    0.48
    ící
    0.47
     букмекерлик
    0.46
    ponsor
    0.45
     الرحيم
    0.44
     దక్షిణ
    0.43
    苍
    0.43
     Thì
    0.43
    POSITIVE LOGITS
    ک
    0.57
    טן
    0.55
    هل
    0.52
    ി
    0.52
    ק
    0.50
    تیب
    0.49
    بین
    0.49
    حال
    0.49
    ب
    0.49
    جمع
    0.47
    Activations Density 0.000%

    No Known Activations