© 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. 102414
    Prev
    Next
    INDEX
    Explanations

    is followed by location or descriptive words

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

    foreign words and symbols

    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
    p
    0.52
    ON
    0.51
     ON
    0.50
    on
    0.47
    ﮈ
    0.46
     också
    0.44
     setImage
    0.44
    c
    0.44
     ken
    0.44
    CN
    0.43
    POSITIVE LOGITS
     работе
    0.48
    ですよね
    0.44
    Tomorrow
    0.44
     tüket
    0.44
    Heute
    0.44
     завтра
    0.44
    Види
    0.44
     причина
    0.44
    Сегодня
    0.44
     Конститу
    0.43
    Activations Density 0.002%

    No Known Activations