© 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. 247774
    Prev
    Next
    INDEX
    Explanations

    Arabic, Russian, or other non-English words

    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
    До
    0.51
    邁
    0.50
    lles
    0.50
    Ệ
    0.49
    Ὀ
    0.47
    ДО
    0.47
    CONNE
    0.47
    긱
    0.47
    욀
    0.46
     eest
    0.46
    POSITIVE LOGITS
     cambió
    0.46
     verificación
    0.45
     হঠাৎ
    0.43
     démon
    0.43
     звезда
    0.43
     FBI
    0.43
     quitting
    0.42
    不存在
    0.42
     accidentally
    0.41
    égi
    0.41
    Activations Density 0.001%

    No Known Activations