© 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. 52495
    Prev
    Next
    INDEX
    Explanations

    related to disclosures and relay

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

    historical context, organization, vital

    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
    incoming
    0.47
    brightness
    0.47
    تی
    0.46
    act
    0.46
    stream
    0.44
    น
    0.44
    தா
    0.43
     brightly
    0.43
    〗
    0.43
    energy
    0.42
    POSITIVE LOGITS
     मौर्य
    0.50
    मिता
    0.45
     letzte
    0.45
     bahawa
    0.44
    愧
    0.44
     acessórios
    0.44
     Durand
    0.43
     任
    0.43
     黃
    0.43
    分為
    0.43
    Activations Density 0.000%

    No Known Activations