© 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. 173236
    Prev
    Next
    INDEX
    Explanations

    places and subjects

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

    specific characteristics or follow-ups

    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
    Klas
    0.53
    ╳
    0.53
     zarówno
    0.52
    Não
    0.50
     auront
    0.48
    椃
    0.48
     Сури
    0.47
    جميع
    0.46
     Certains
    0.46
    ί
    0.46
    POSITIVE LOGITS
     spleen
    0.56
     sputum
    0.53
     xenon
    0.52
     further
    0.51
     ventilation
    0.50
     spermatozoa
    0.50
     coating
    0.50
     centrifugation
    0.49
     elongation
    0.49
     larva
    0.48
    Activations Density 0.001%

    No Known Activations