© 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. 150646
    Prev
    Next
    INDEX
    Explanations

    documentary films

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

    dramatic lighting

    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
    ong
    0.54
    ukt
    0.49
    o
    0.46
    assembly
    0.45
    ktu
    0.45
    andi
    0.45
    tran
    0.44
     foundation
    0.44
    ourcen
    0.44
    ției
    0.44
    POSITIVE LOGITS
     evaded
    0.59
    乒
    0.54
    ໊
    0.54
    诈
    0.52
    马
    0.50
    鸭
    0.50
     солдат
    0.50
     víctima
    0.49
    平
    0.49
     soldado
    0.49
    Activations Density 0.000%

    No Known Activations