© 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. 51307
    Prev
    Next
    INDEX
    Explanations

    Russia suspend outlaw

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

    Russian composers and music streaming

    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
     втра
    0.44
     cemetery
    0.43
    Herk
    0.42
     বিবাহের
    0.42
     пов
    0.41
    㸵
    0.41
    变形
    0.40
    pham
    0.39
    
    0.39
    可选
    0.39
    POSITIVE LOGITS
    വാദ
    0.39
    wit
    0.38
     reluct
    0.37
    outil
    0.37
    wap
    0.37
     bakan
    0.37
     straks
    0.37
    色は
    0.36
    auce
    0.36
    ucional
    0.36
    Activations Density 0.003%

    No Known Activations