© 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. 116076
    Prev
    Next
    INDEX
    Explanations

    cards and steel floor

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

    language identification

    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
     attenuation
    0.50
     administra
    0.49
     simple
    0.47
     cade
    0.46
     one
    0.45
     administration
    0.45
     ち
    0.45
     billing
    0.44
     policy
    0.43
     mét
    0.43
    POSITIVE LOGITS
    oises
    0.48
    😐
    0.48
     непоня
    0.47
    рики
    0.47
    нома
    0.46
    ！？
    0.46
    嶷
    0.45
    缨
    0.45
    уга
    0.44
     खुलने
    0.44
    Activations Density 0.000%

    No Known Activations