© 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. 32763
    Prev
    Next
    INDEX
    Explanations

    end of sentence or clause

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

    vision and

    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
     v
    0.34
     not
    0.34
     bath
    0.34
     tid
    0.32
     rot
    0.32
     claiming
    0.31
     home
    0.30
     nutrient
    0.30
     reap
    0.30
     characterized
    0.30
    POSITIVE LOGITS
    嘹
    0.42
    краё
    0.40
     специальности
    0.39
    ารย์
    0.39
     невро
    0.39
     нер
    0.37
    瑛
    0.37
    ुप
    0.36
     осмо
    0.36
    MiddleLine
    0.36
    Activations Density 0.011%

    No Known Activations