© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1961
    Prev
    Next
    INDEX
    Explanations

    steel and metal parts

    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_40_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
    药物
    0.51
     ওষুধের
    0.51
     細胞
    0.50
    🥑
    0.50
    孢
    0.47
    кмекер
    0.46
     Verbal
    0.46
    🍉
    0.46
     PLHIV
    0.46
    酵素
    0.45
    POSITIVE LOGITS
     steel
    2.27
     metal
    2.25
     metals
    2.17
     alloys
    1.98
     alloy
    1.97
     metallic
    1.95
    金属
    1.95
     metallurgy
    1.93
    metal
    1.90
    steel
    1.90
    Activations Density 0.103%

    No Known Activations