© 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. 90599
    Prev
    Next
    INDEX
    Explanations

    return new

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

    programming code initialization

    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
     रेजि
    0.39
    веден
    0.37
    số
    0.37
     ৪০
    0.37
    ету
    0.37
    ၄
    0.37
    යු
    0.36
    ев
    0.35
    ЕС
    0.35
    зию
    0.35
    POSITIVE LOGITS
     unui
    0.52
     new
    0.49
     einem
    0.47
     새로운
    0.47
     sebuah
    0.46
    一个新的
    0.45
     unei
    0.44
     isang
    0.44
    new
    0.41
     einer
    0.41
    Activations Density 0.000%

    No Known Activations