© 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. 149050
    Prev
    Next
    INDEX
    Explanations

    specific following word

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

    explaining or clarifying situations

    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
     നിറ
    0.44
     शतक
    0.44
    屉
    0.43
     oggi
    0.42
     Oggi
    0.41
    饰
    0.41
    秸
    0.41
    媳
    0.41
    电气
    0.40
    anbul
    0.40
    POSITIVE LOGITS
    spruch
    0.50
     этот
    0.46
     deduction
    0.42
     "-",
    0.42
    тою
    0.41
     añadido
    0.40
     ruining
    0.40
    еры
    0.40
    фф
    0.40
    чет
    0.40
    Activations Density 0.001%

    No Known Activations