© 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. 90501
    Prev
    Next
    INDEX
    Explanations

    indicating specific entities or domains

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

    strategies for beginners

    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
    玠
    0.46
     esoteric
    0.45
    बॉलीवुड
    0.43
     pathologies
    0.42
     collaborations
    0.41
    锜
    0.41
    Detal
    0.41
    痧
    0.40
     Cables
    0.39
    获
    0.39
    POSITIVE LOGITS
     commitment
    0.48
    温暖
    0.47
     ниво
    0.47
     JPMorgan
    0.46
    ールの
    0.46
     गार
    0.46
     शिफ्ट
    0.46
     зміню
    0.46
     अपडेट
    0.45
     बदलने
    0.45
    Activations Density 0.000%

    No Known Activations