© 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. 66013
    Prev
    Next
    INDEX
    Explanations

    website andsubstances andsmartphone. Butarea thatto hisin thesurvey, thestage forterm “FHIRpower”

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

    technical terms or specific concepts

    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
    㴡
    0.49
    覺得
    0.48
    ॉक
    0.46
     Shrewsbury
    0.45
     âng
    0.43
    ों
    0.43
     lập
    0.43
    णे
    0.43
    想法
    0.42
    ίνη
    0.42
    POSITIVE LOGITS
    ហើយ
    0.47
    ثیر
    0.47
    ີ່
    0.46
    riumph
    0.46
    MDg
    0.46
    HIS
    0.45
    Html
    0.45
    ᆯ
    0.45
    Pokud
    0.43
    Acces
    0.43
    Activations Density 0.001%

    No Known Activations