© 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. 111466
    Prev
    Next
    INDEX
    Explanations

    restricted content

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

    darkness and silence

    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
    Lead
    0.47
    軍
    0.46
    ऊन
    0.46
     модуль
    0.45
     Rabu
    0.44
    動
    0.43
     செறிவு
    0.43
    邪魔
    0.43
    鬱
    0.42
    Native
    0.41
    POSITIVE LOGITS
    বিজ
    0.51
    দৃশ্য
    0.47
     Бан
    0.47
    єр
    0.46
    ənd
    0.45
    cipher
    0.45
     bulging
    0.45
    ণ্য
    0.45
    ே
    0.45
    ḍ
    0.44
    Activations Density 0.000%

    No Known Activations