© 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. 133914
    Prev
    Next
    INDEX
    Explanations

    pharmacy, insurance, or medical product information

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

    language sections

    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
    盜
    0.44
    atamente
    0.43
    )$$
    0.43
    adamente
    0.41
     লিমি
    0.41
    옛
    0.41
    盗
    0.40
    ленно
    0.39
    ஷ
    0.38
    寡
    0.38
    POSITIVE LOGITS
     konular
    0.48
    WithString
    0.48
     onderwerp
    0.48
     عربي
    0.46
     hoofdst
    0.46
     stvar
    0.46
     angust
    0.45
     ceinture
    0.45
     pemrograman
    0.45
     стрель
    0.45
    Activations Density 0.001%

    No Known Activations