© 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. 122808
    Prev
    Next
    INDEX
    Explanations

    advancing stages or director titles

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

    names and technical terms

    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
    ק
    0.56
    ਲ
    0.54
    प
    0.50
    п
    0.49
    ج
    0.49
    تب
    0.49
    پ
    0.49
    ક
    0.49
    ك
    0.47
    ENT
    0.47
    POSITIVE LOGITS
     начали
    0.52
     tennis
    0.51
     khán
    0.51
     recharged
    0.49
     biên
    0.48
     recharge
    0.48
     Tennis
    0.47
     बांग्लादेश
    0.46
     chargingStation
    0.46
     chặn
    0.46
    Activations Density 0.000%

    No Known Activations