© 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. 152086
    Prev
    Next
    INDEX
    Explanations

    business and legal terms

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

    travel info, Speyside malt

    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
     פס
    0.44
     ψ
    0.44
     Subsec
    0.41
     southeast
    0.41
     ዘ
    0.41
     scrambled
    0.41
    )(
    0.41
     ولا
    0.40
     expended
    0.40
     perturbed
    0.40
    POSITIVE LOGITS
     ОК
    0.50
    jač
    0.50
    제
    0.49
    directions
    0.49
     Unterstützung
    0.48
     घटस्फोट
    0.48
     미리
    0.48
     സർക്കാർ
    0.48
    विता
    0.47
     पार्टनर
    0.47
    Activations Density 0.000%

    No Known Activations