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. 293
    Prev
    Next
    INDEX
    Explanations

    table summarizing differences

    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
     only
    0.64
    ?
    0.64
    only
    0.64
     tears
    0.62
    tend
    0.61
    Leave
    0.59
      
    0.59
    |
    0.57
     |
    0.56
    se
    0.56
    POSITIVE LOGITS
    --------------
    1.50
    ---------------
    1.49
    ……………………
    1.40
    ----------------
    1.38
    -------------
    1.38
    ………………………………
    1.29
    -----------
    1.26
     ……………………
    1.24
     ==============
    1.23
    ------------
    1.22
    Activations Density 0.052%

    No Known Activations