© 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. 177558
    Prev
    Next
    INDEX
    Explanations

    producing outcomes

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

    list items and code snippets

    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
     企业
    0.48
    un
    0.47
    si
    0.47
     نصی
    0.47
    represents
    0.47
     هنا
    0.46
    ik
    0.46
    ꒳
    0.45
    aton
    0.45
    means
    0.45
    POSITIVE LOGITS
     monetize
    0.48
     monitoring
    0.48
     surveillance
    0.47
     concl
    0.47
     HBC
    0.47
     tubo
    0.46
    ्यू
    0.46
     basement
    0.46
     mobilize
    0.46
     mainline
    0.45
    Activations Density 0.000%

    No Known Activations