© 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. 234505
    Prev
    Next
    INDEX
    Explanations

    kyocera

    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
    ՜
    0.51
     imminent
    0.49
    핑
    0.46
    å
    0.45
    TA
    0.44
    ্কৃতিক
    0.44
    $\
    0.43
    روح
    0.42
    定制
    0.42
    ์
    0.42
    POSITIVE LOGITS
    acidade
    0.55
     сохранить
    0.50
     সুযোগ
    0.49
    зяй
    0.49
     আসে
    0.47
     sağlam
    0.47
     Сы
    0.46
     রোগীদের
    0.46
     студен
    0.46
     Prakash
    0.45
    Activations Density 0.002%

    No Known Activations