© 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. 48021
    Prev
    Next
    INDEX
    Explanations

    head of class or automated profile

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

    constant in

    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
    an
    0.56
    vert
    0.47
     Cheryl
    0.47
     Olivia
    0.46
     oligarch
    0.46
    abod
    0.45
     ನಾವು
    0.45
    鬻
    0.45
     उक्त
    0.44
    đ
    0.44
    POSITIVE LOGITS
    CriteriaUtils
    0.55
    مني
    0.49
    َ
    0.47
    त्रेयी
    0.47
    PropertyParam
    0.46
    Synthetic
    0.46
     الآخر
    0.45
     conveys
    0.45
     عليه
    0.45
    Repositories
    0.45
    Activations Density 0.000%

    No Known Activations