© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 4809
    Prev
    Next
    INDEX
    Explanations

    try...except blocks

    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_65k_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
    TakeVideo
    0.77
    lios
    0.76
    numberOfRecords
    0.74
    Ѳ
    0.74
    <0xB4>
    0.72
    یب
    0.72
     కూడా
    0.72
    婳
    0.72
    CommandLine
    0.72
    )].
    0.71
    POSITIVE LOGITS
     models
    0.66
    in
    0.62
     modeller
    0.61
    models
    0.61
     Mons
    0.60
     ACE
    0.60
     tarihinde
    0.59
    off
    0.58
    ACE
    0.57
    hungry
    0.57
    Activations Density 0.128%

    No Known Activations