© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24132
    Prev
    Next
    INDEX
    Explanations

    tusks, DUS, TUS, BLE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    聝
    0.41
    raquinone
    0.40
    祿
    0.39
     ইলেক্ট্রোড
    0.38
     ود
    0.37
    彻底
    0.37
     লুকিয়ে
    0.37
     Lui
    0.37
    ㅃ
    0.37
    㽛
    0.37
    POSITIVE LOGITS
    antara
    0.45
     disturbed
    0.41
     warm
    0.40
     Tus
    0.39
     hust
    0.39
     hustle
    0.38
    ಂತರ
    0.38
     fragrant
    0.38
    calo
    0.38
     disturb
    0.37
    Activations Density 0.004%

    No Known Activations