© 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. 138511
    Prev
    Next
    INDEX
    Explanations

    sports and events

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

    launching things, definitions, traditional models

    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
     chay
    0.47
    ු
    0.43
    상의
    0.42
     clams
    0.42
     convolution
    0.41
     cosmetology
    0.41
    மன்ற
    0.40
     constructs
    0.40
     mh
    0.40
     processor
    0.39
    POSITIVE LOGITS
    λαν
    0.48
     notícia
    0.47
    岩
    0.47
    ána
    0.46
    ména
    0.46
    🏁
    0.45
    赛事
    0.45
    णू
    0.44
    oub
    0.44
    ед
    0.44
    Activations Density 0.002%

    No Known Activations