© 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. 59054
    Prev
    Next
    INDEX
    Explanations

    also known as

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

    websites, loading, participle

    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
    밖
    0.45
    ध्व
    0.44
     graz
    0.42
     Ds
    0.41
    ⋅
    0.41
     explodes
    0.39
     Rie
    0.38
    までは
    0.38
    ყვ
    0.38
    Summary
    0.38
    POSITIVE LOGITS
    de
    0.48
    ت
    0.48
    נ
    0.46
    ר
    0.45
    ット
    0.44
     نم
    0.44
    деги
    0.43
     hyphen
    0.43
     অভিন
    0.43
    ב
    0.43
    Activations Density 0.001%

    No Known Activations