© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22936
    Prev
    Next
    INDEX
    Explanations

    range(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     computational
    0.45
     cały
    0.45
    ండ
    0.44
    㼛
    0.44
    䛶
    0.43
    蚓
    0.42
    欬
    0.42
     lenguaje
    0.42
     برنامج
    0.41
     vVertex
    0.41
    POSITIVE LOGITS
    ตั้งแต่
    0.48
    uscany
    0.44
    Native
    0.43
    ^{+},
    0.43
    insk
    0.42
    inis
    0.42
    odia
    0.42
    INI
    0.42
    au
    0.41
    開始
    0.41
    Activations Density 0.028%

    No Known Activations