© 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. 117712
    Prev
    Next
    INDEX
    Explanations

    wedding ceremonies

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

    explaining terms and definitions

    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
     सीधा
    0.49
    .*
    0.48
    mmm
    0.48
     modelo
    0.46
    iframe
    0.46
     Bolsa
    0.46
    mmmm
    0.46
    ps
    0.44
     }
    0.44
     km
    0.44
    POSITIVE LOGITS
    쾌
    0.49
     Krzy
    0.45
    Ᏺ
    0.44
     krzy
    0.44
    诵
    0.43
     Kenyatta
    0.43
    积
    0.43
    昕
    0.43
     słu
    0.42
    ፩
    0.42
    Activations Density 0.000%

    No Known Activations