© 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. 35142
    Prev
    Next
    INDEX
    Explanations

    requests for email or post

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

    API requests and parameters

    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
    ICON
    0.45
    iches
    0.45
    ческих
    0.44
     свойства
    0.43
    feat
    0.42
    🩺
    0.41
    깨
    0.40
    수상
    0.39
     бывает
    0.39
     நடித்து
    0.39
    POSITIVE LOGITS
     requesting
    0.66
     request
    0.62
     请求
    0.61
     Request
    0.58
     transaction
    0.57
    请求
    0.57
     requested
    0.56
     meminta
    0.55
     required
    0.52
    Request
    0.52
    Activations Density 0.006%

    No Known Activations