© 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. 192104
    Prev
    Next
    INDEX
    Explanations

    specific contexts, foreign scripts

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

    analytics, arguments, policy

    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
     Frédéric
    0.55
     gala
    0.54
     vinos
    0.54
    톨
    0.53
    ³,
    0.52
     dynasties
    0.52
     hérit
    0.52
     démont
    0.52
     régime
    0.51
     vín
    0.49
    POSITIVE LOGITS
    elajaran
    0.50
    ambulance
    0.47
    强烈
    0.47
    涉
    0.46
    ắm
    0.46
     копия
    0.44
    羚
    0.44
    uerung
    0.44
    assing
    0.44
     проекти
    0.43
    Activations Density 0.000%

    No Known Activations