© 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. 87795
    Prev
    Next
    INDEX
    Explanations

    accounting and beyond

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

    sales and marketing

    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
    careers
    0.55
    під
    0.53
    施設の
    0.52
    ต
    0.52
    ы
    0.50
    เด
    0.50
    funktionen
    0.49
    products
    0.47
    interesse
    0.46
    contracts
    0.46
    POSITIVE LOGITS
     Baseline
    0.48
     springboard
    0.48
     gian
    0.44
    彪
    0.43
     exodus
    0.42
     biographical
    0.42
    INOIS
    0.42
     KPK
    0.41
     VPD
    0.41
     continuation
    0.41
    Activations Density 0.000%

    No Known Activations