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. 377
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ↵↵
    0.53
    et
    0.41
    ic
    0.36
    u
    0.36
    en
    0.34
    or
    0.33
     somewhat
    0.33
    ↵↵↵↵
    0.33
    al
    0.32
     still
    0.31
    POSITIVE LOGITS
    <unused2151>
    0.67
     Specifically
    0.66
     Consequently
    0.64
     Their
    0.61
     Therefore
    0.61
     Basically
    0.59
     Examples
    0.58
     Thus
    0.57
     Misalnya
    0.57
     Whenever
    0.56
    Activations Density 2.495%

    No Known Activations