© 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. 86641
    Prev
    Next
    INDEX
    Explanations

    repertoire catalogs

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

    biology studies elements

    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
    ott
    0.42
     डाली
    0.38
     लाइट्स
    0.38
    霾
    0.38
    ắt
    0.37
     घेत
    0.37
    อล
    0.37
    ěž
    0.37
     предстоя
    0.37
     highlights
    0.36
    POSITIVE LOGITS
     інших
    0.47
     abandon
    0.47
     scrivere
    0.46
     대체
    0.46
     Совет
    0.45
    嗄
    0.45
    ivamente
    0.44
    を行
    0.44
    шон
    0.44
    chard
    0.43
    Activations Density 0.000%

    No Known Activations