© 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. 87618
    Prev
    Next
    INDEX
    Explanations

    multilingual content detection

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

    structures and patterns

    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
    paces
    0.53
    𝕝
    0.47
     तालुका
    0.46
    পালা
    0.45
     लक
    0.45
     माणसा
    0.45
     বাহিরে
    0.44
     subsidence
    0.44
    𝕡
    0.44
    ights
    0.44
    POSITIVE LOGITS
    Opinion
    0.42
     profoundly
    0.41
     Avrupa
    0.40
    送
    0.39
     Auft
    0.39
     Senin
    0.39
     Boost
    0.39
    arynge
    0.39
    дж
    0.38
     Mourinho
    0.38
    Activations Density 0.001%

    No Known Activations