Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9779
    Prev
    Next
    INDEX
    Explanations

    metals and their properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
     Srivastava
    0.97
     Sticky
    0.86
    Sticky
    0.82
    LayoutStyle
    0.80
     DataSource
    0.80
     কাদ
    0.79
    𝔰
    0.79
    Strawberry
    0.78
    俞
    0.77
     Tufts
    0.77
    POSITIVE LOGITS
     metal
    2.31
     metals
    2.29
     steel
    2.12
     metallic
    2.08
     copper
    2.06
     stainless
    1.96
     metall
    1.96
     Metal
    1.93
    金属
    1.93
    Metal
    1.85
    Activations Density 0.277%

    No Known Activations