© 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. 97949
    Prev
    Next
    INDEX
    Explanations

    possible inassociated withreserved forto put

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

    names and specific terms

    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
    PARATOR
    0.50
     дописа
    0.50
    Aik
    0.48
    noduch
    0.46
    鬨
    0.46
    URANCE
    0.44
    γεν
    0.44
    鍏
    0.44
    nvarchar
    0.43
    的人物
    0.43
    POSITIVE LOGITS
     [
    0.52
     videos
    0.48
     [(
    0.43
     still
    0.43
    ্যানে
    0.43
     аны
    0.43
     giáo
    0.42
     doable
    0.42
     ($\
    0.42
     dared
    0.42
    Activations Density 0.000%

    No Known Activations