© 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. 13303
    Prev
    Next
    INDEX
    Explanations

    first names followed by surnames

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

    market, investments, or alternatives

    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
     też
    0.55
    そして
    0.46
    氲
    0.44
    ە
    0.43
     таксама
    0.42
    যাপন
    0.42
    荪
    0.42
     prze
    0.42
    ാല
    0.41
    ຂອງ
    0.41
    POSITIVE LOGITS
     veya
    0.83
     или
    0.80
     alebo
    0.75
     或
    0.73
     yoki
    0.73
     ಅಥವಾ
    0.71
     หรือ
    0.70
     અથવા
    0.69
     কিংবা
    0.68
     또는
    0.68
    Activations Density 0.000%

    No Known Activations