© 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. 187871
    Prev
    Next
    INDEX
    Explanations

    IT, medical, business, forums

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

    investment, comfort, Temporarily, South, Brenda

    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
     کسب
    0.53
     معامل
    0.45
     หลัก
    0.44
     攵
    0.44
     odred
    0.44
     هند
    0.43
     эффек
    0.43
     dino
    0.43
     contentView
    0.43
     kicker
    0.42
    POSITIVE LOGITS
     Pois
    0.48
    {},
    0.45
    ία
    0.44
    ispiels
    0.44
    գ
    0.43
    мих
    0.43
    igian
    0.42
    ან
    0.41
    नै
    0.41
    },-\
    0.41
    Activations Density 0.001%

    No Known Activations