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. 22-GEMMASCOPE-2-RES-16K
    4. 201
    Prev
    Next
    INDEX
    Explanations

    Notable people's last names

    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
     
    0.81
     be
    0.77
      
    0.68
     int
    0.67
     a
    0.67
     *
    0.66
     tangible
    0.65
     nut
    0.65
     q
    0.64
     input
    0.64
    POSITIVE LOGITS
    ková
    1.29
    kowski
    1.18
    ković
    1.15
    opoulos
    1.11
     ಅವರು
    1.10
    ansky
    1.09
     afirmó
    1.09
    owski
    1.08
     afirmou
    1.07
    ński
    1.07
    Activations Density 0.155%

    No Known Activations