© 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. 182590
    Prev
    Next
    INDEX
    Explanations

    measurements and specifications

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

    cosmological, codebase, word, atmosphere, act, figures

    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
    ☀️
    0.47
     lonely
    0.46
     whitelist
    0.44
    はじめ
    0.43
     Findlay
    0.43
     girly
    0.42
     crappy
    0.42
    ynchron
    0.42
    Еще
    0.41
    tsioon
    0.41
    POSITIVE LOGITS
    к
    0.50
     ପ୍ର
    0.48
    َس
    0.47
    ловой
    0.47
    鬻
    0.46
     금액
    0.45
    ত্য
    0.45
     согласо
    0.44
     Nigerians
    0.42
     宮
    0.42
    Activations Density 0.001%

    No Known Activations