© 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. 32029
    Prev
    Next
    INDEX
    Explanations

    assist with content

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

    date types

    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
     Beasley
    0.44
     অন্যের
    0.43
    ższej
    0.43
     bulun
    0.42
    cedent
    0.41
    idE
    0.41
     errand
    0.41
    씌
    0.40
     Erskine
    0.40
    isał
    0.40
    POSITIVE LOGITS
    什么时候
    0.38
     поверх
    0.38
    鋰
    0.37
    譜
    0.36
     musical
    0.36
     твор
    0.36
     музыка
    0.36
     выбрать
    0.36
    ГЭ
    0.36
    तिम
    0.35
    Activations Density 0.001%

    No Known Activations