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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 694
    Prev
    Next
    INDEX
    Explanations

    mathematical multiplication operations

    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_29_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
    说到
    0.57
     firefighting
    0.53
    ほとんど
    0.52
     searchable
    0.52
     //
    0.51
     Delphi
    0.51
     mostly
    0.50
     **
    0.49
    **
    0.48
     Anthrop
    0.48
    POSITIVE LOGITS
    cdot
    1.37
    left
    1.18
    times
    1.13
    text
    1.02
    sqrt
    1.00
    frac
    0.98
    Rightarrow
    0.94
    therefore
    0.90
    cdots
    0.89
    ldots
    0.88
    Activations Density 0.024%

    No Known Activations