© 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. 189312
    Prev
    Next
    INDEX
    Explanations

    recent grads

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

    about building or improving

    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
    Р
    0.62
    Щ
    0.54
    Б
    0.54
    ৪
    0.52
    Packet
    0.51
    Т
    0.51
    ა
    0.51
    Ш
    0.49
    Espagne
    0.49
    Л
    0.49
    POSITIVE LOGITS
     Decentral
    0.52
    eras
    0.50
     Autonomous
    0.48
     Cognitive
    0.47
     Start
    0.47
     Brava
    0.47
     Dollars
    0.46
     Aloha
    0.45
    itos
    0.44
     BorderLayout
    0.44
    Activations Density 0.000%

    No Known Activations