© 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. 103913
    Prev
    Next
    INDEX
    Explanations

    recognized your skill

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

    sustainability and reporting

    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
    <unused58>
    0.51
    Of
    0.50
    Nathan
    0.48
    ඛ
    0.48
    David
    0.47
    ጣት
    0.46
    颛
    0.46
    widgetTo
    0.46
    Antoine
    0.46
    <?
    0.45
    POSITIVE LOGITS
     hosped
    0.47
     mcm
    0.46
     básicas
    0.46
     непри
    0.44
     tecnológica
    0.44
     típica
    0.43
     log
    0.42
    飯店
    0.42
     технологи
    0.42
     clínica
    0.41
    Activations Density 0.000%

    No Known Activations