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. 3719
    Prev
    Next
    INDEX
    Explanations

    numbers separated by dots or hyphens

    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
     etc
    0.76
    नेशन
    0.71
    etc
    0.66
     hundreds
    0.65
    Hundreds
    0.65
     وغيرها
    0.65
    阡
    0.64
    oticons
    0.64
    tty
    0.63
     dajj
    0.63
    POSITIVE LOGITS
    -
    0.95
    屆
    0.90
     দশমিক
    0.89
     Послед
    0.82
    mise
    0.82
     zák
    0.81
    錆
    0.80
    .
    0.80
     leis
    0.79
     crise
    0.79
    Activations Density 0.356%

    No Known Activations