© 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. 136779
    Prev
    Next
    INDEX
    Explanations

    apostle Paul, maiden tag, silver glass

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

    life, emotional, cycle, left side

    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
    ើ
    0.48
    ت
    0.44
    テナンス
    0.43
     transmits
    0.42
    鑒
    0.42
    \]
    0.41
    धि
    0.41
    اً
    0.39
    ग्र
    0.38
    исто
    0.38
    POSITIVE LOGITS
    ьому
    0.43
     brak
    0.43
    smiling
    0.42
    textbackslash
    0.42
     hectic
    0.42
     sassy
    0.40
    s
    0.40
    లపై
    0.40
     päät
    0.39
     employability
    0.39
    Activations Density 0.002%

    No Known Activations