© 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. 188964
    Prev
    Next
    INDEX
    Explanations

    quantity followed by figure

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

    effective, funny, absurd

    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
    ים
    0.48
    鋲
    0.48
    स्टूड
    0.47
    뗀
    0.46
    얇
    0.46
    ཥ
    0.45
    ᑦ
    0.45
    s
    0.44
    ཊ
    0.44
    옅
    0.44
    POSITIVE LOGITS
     procedura
    0.49
     chases
    0.47
     forg
    0.47
    ত্তা
    0.46
     deme
    0.46
    দিগকে
    0.46
     sendiri
    0.46
    িবার
    0.46
     tersedia
    0.45
     werde
    0.45
    Activations Density 0.006%

    No Known Activations