© 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. 48975
    Prev
    Next
    INDEX
    Explanations

    want to

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

    trainer and client dynamics

    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
    3
    0.53
    1
    0.52
    ko
    0.51
    h
    0.51
    4
    0.49
    ud
    0.48
    p
    0.47
    0
    0.47
    fd
    0.46
    ab
    0.46
    POSITIVE LOGITS
     tens
    0.49
     sinusoidal
    0.48
     taco
    0.47
     десятки
    0.47
     காட்ச
    0.47
     інші
    0.47
     теат
    0.46
     المزيد
    0.46
     түр
    0.46
     Мы
    0.46
    Activations Density 0.000%

    No Known Activations