© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32659
    Prev
    Next
    INDEX
    Explanations

    giver her, permitting understanding, rest her

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

    votes or actions

    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
    achev
    0.43
    د
    0.43
    "
    0.43
    Tienes
    0.42
    um
    0.41
     concepts
    0.41
     Of
    0.40
    concepts
    0.39
     sätt
    0.39
    Harvest
    0.39
    POSITIVE LOGITS
     تعلمنا
    0.50
    翻译
    0.46
    缓冲
    0.45
    無し
    0.44
    的功能
    0.44
     sonho
    0.44
     facto
    0.43
    )}}{\
    0.43
    翻譯
    0.43
     none
    0.42
    Activations Density 0.000%

    No Known Activations