© 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. 129460
    Prev
    Next
    INDEX
    Explanations

    foreign or niche words

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

    figurative language or technical terms

    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
     televiz
    0.57
     தொலைக்கா
    0.52
     television
    0.52
     पका
    0.51
     টেলিভিশন
    0.50
     تلویزی
    0.49
     ی
    0.49
     도시
    0.49
    vislosti
    0.49
     телевиде
    0.49
    POSITIVE LOGITS
    плат
    0.44
    нова
    0.44
     Sl
    0.41
    εί
    0.40
     Rook
    0.40
    সমূহ
    0.39
     functor
    0.39
     Shib
    0.39
     Cruiser
    0.39
    ες
    0.39
    Activations Density 0.000%

    No Known Activations