© 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. 117616
    Prev
    Next
    INDEX
    Explanations

    distributors page, next step

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

    explanation and rewrite

    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
    دا
    0.49
     של
    0.45
    ı
    0.43
    )}(\
    0.41
    جع
    0.41
     audiovis
    0.41
     vektor
    0.41
    ؛
    0.41
     kes
    0.41
     distrib
    0.41
    POSITIVE LOGITS
    recipe
    0.45
     churches
    0.44
    পৌ
    0.43
    榆
    0.42
     বগু
    0.41
     গেলে
    0.40
     中古
    0.40
    有可能
    0.40
     గ్రామ
    0.40
    oya
    0.39
    Activations Density 0.005%

    No Known Activations