© 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. 98005
    Prev
    Next
    INDEX
    Explanations

    after certain word

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

    special characters, definitions, or pauses

    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
    もあり
    0.48
    ป
    0.45
    د
    0.44
    誘
    0.44
    ת
    0.43
    íf
    0.42
    5
    0.42
    ків
    0.42
     Cái
    0.41
    と言
    0.41
    POSITIVE LOGITS
    的需求
    0.49
    的企业
    0.45
    Unis
    0.45
     શિક્ષણ
    0.45
     ক্র
    0.44
    ।...
    0.44
    :</
    0.43
    ोलॉजी
    0.43
    strup
    0.42
    playSound
    0.42
    Activations Density 0.002%

    No Known Activations