© 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. 187473
    Prev
    Next
    INDEX
    Explanations

    aid help helping

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

    help and aids

    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
     IRI
    0.48
     ય
    0.47
     কেহ
    0.46
     Norden
    0.44
     YES
    0.43
    рити
    0.42
     Ри
    0.42
    媒體
    0.42
    ？！
    0.42
    Santo
    0.42
    POSITIVE LOGITS
     ช่วย
    0.50
     ayudar
    0.49
     aider
    0.49
     segí
    0.46
     helpen
    0.46
    锥
    0.46
     ajudar
    0.45
     hjæl
    0.45
     تساعد
    0.44
    GradientPanel
    0.44
    Activations Density 0.000%

    No Known Activations