© 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. 187799
    Prev
    Next
    INDEX
    Explanations

    following certain words

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

    KDE Connect, you say

    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
     espécie
    0.48
     Holi
    0.46
     bhave
    0.45
    ğinin
    0.43
     জগতের
    0.43
    *'
    0.43
     Seperti
    0.43
     seperti
    0.42
     gibi
    0.42
     crackers
    0.42
    POSITIVE LOGITS
    طقة
    0.49
    订
    0.49
    邮
    0.47
    县
    0.47
    County
    0.46
    oscopy
    0.46
    iono
    0.45
     اعظم
    0.44
    IDX
    0.44
    婴儿
    0.44
    Activations Density 0.000%

    No Known Activations