© 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. 49815
    Prev
    Next
    INDEX
    Explanations

    services or instructions

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

    business and technical 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
    غة
    0.48
     beth
    0.46
     Dor
    0.45
    مال
    0.44
    ری
    0.44
     caract
    0.44
     thes
    0.44
    텁
    0.44
     Beth
    0.43
    itale
    0.43
    POSITIVE LOGITS
     অস্বীকার
    0.47
    排放
    0.43
     expropri
    0.43
     neutrinos
    0.42
     shoppers
    0.41
     প্রতিরোধ
    0.41
     కానీ
    0.41
     কূটনীতিক
    0.41
     plasmids
    0.41
    np
    0.41
    Activations Density 0.001%

    No Known Activations