© 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. 72089
    Prev
    Next
    INDEX
    Explanations

    Foreign interests, application to

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

    urgency and purpose

    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
    બો
    0.46
    دة
    0.45
    અમ
    0.44
    ौरी
    0.42
    痳
    0.42
     necessari
    0.42
    თ
    0.41
    ORD
    0.41
    магази
    0.41
     plantation
    0.41
    POSITIVE LOGITS
    ဆံ
    0.52
    </h3>
    0.46
     seguros
    0.45
    letal
    0.45
     alerting
    0.45
    itif
    0.44
    Elim
    0.43
     অত্যন্ত
    0.43
    openweathermap
    0.43
     alertness
    0.43
    Activations Density 0.000%

    No Known Activations