© 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. 154408
    Prev
    Next
    INDEX
    Explanations

    seizing firearms

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

    building, investigation, catnip toys, further evaluation

    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
    忍者
    0.54
     Fonbet
    0.52
    斎
    0.52
    transform
    0.51
    范围内
    0.49
    isdir
    0.49
    seleccion
    0.49
    範囲
    0.49
    alumno
    0.48
    signin
    0.48
    POSITIVE LOGITS
     bundles
    0.54
     pavements
    0.49
    -
    0.49
     installations
    0.47
     establishments
    0.47
     inspiration
    0.45
     chromosomes
    0.45
     textbooks
    0.44
     alarms
    0.44
     expertise
    0.44
    Activations Density 0.000%

    No Known Activations