© 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. 59188
    Prev
    Next
    INDEX
    Explanations

    domain names and urls

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

    . / GUI / . \ \ Poisson model

    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
     AISI
    0.38
     ప్రారం
    0.38
    ate
    0.38
    <unused477>
    0.36
     रौनक
    0.36
     של
    0.36
    ineties
    0.35
    ifferenti
    0.35
     isotropy
    0.35
    wells
    0.35
    POSITIVE LOGITS
    之前
    0.39
    льный
    0.38
     believe
    0.37
    icado
    0.37
     ಅವರ
    0.36
    ično
    0.36
    ricao
    0.36
    ಈ
    0.34
    認為
    0.34
    ीडियो
    0.34
    Activations Density 0.001%

    No Known Activations