© 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. 178844
    Prev
    Next
    INDEX
    Explanations

    公寓 越层

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

    about warmer

    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
    ತ್ಯ
    0.54
    놔
    0.47
    νια
    0.47
    ਣੀ
    0.46
    кти
    0.45
    ন
    0.45
    नव
    0.45
    нды
    0.45
    νης
    0.45
    ЕЛ
    0.44
    POSITIVE LOGITS
     fleeting
    0.47
     一个
    0.45
     这些
    0.44
     ephemeral
    0.44
     über
    0.44
     চিত্ত
    0.43
     لوبو
    0.43
    ong
    0.42
     ල
    0.42
     وهذه
    0.42
    Activations Density 0.000%

    No Known Activations