© 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. 22443
    Prev
    Next
    INDEX
    Explanations

    coming to

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

    can bypass

    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
     Watercolour
    0.48
     Festival
    0.45
     Forestry
    0.45
     Society
    0.43
     Word
    0.43
     Disease
    0.43
    ณี
    0.42
    邗
    0.42
     Barnard
    0.42
     Smithsonian
    0.41
    POSITIVE LOGITS
     juguete
    0.50
     juguetes
    0.49
    ры
    0.49
     plataforma
    0.47
    رفة
    0.47
     nuevos
    0.46
     múltipl
    0.46
     desarroll
    0.45
     espera
    0.45
     periodistas
    0.45
    Activations Density 0.000%

    No Known Activations