© 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. 47210
    Prev
    Next
    INDEX
    Explanations

    built purpose of

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

    avoiding heat, seeking shade

    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
    鸨
    0.50
    奏
    0.46
    舌
    0.44
    tble
    0.44
    犟
    0.44
    Genres
    0.43
    Cone
    0.43
     বাদী
    0.43
    เชสเตอร์
    0.42
    FlashValue
    0.42
    POSITIVE LOGITS
    vip
    0.51
    0
    0.51
    h
    0.50
     tận
    0.48
    ̃
    0.48
    নিয়
    0.46
    er
    0.46
     সেনান
    0.46
    og
    0.45
    Y
    0.45
    Activations Density 0.000%

    No Known Activations