© 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-262K
    7. 5842
    Prev
    Next
    INDEX
    Explanations

    list formatting and special characters

    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_262k_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
    on
    0.72
     e
    0.71
     pre
    0.70
     app
    0.70
     Facebook
    0.68
    man
    0.68
     back
    0.64
     n
    0.62
     s
    0.62
     (
    0.62
    POSITIVE LOGITS
    hôpital
    1.19
    <unused1908>
    1.11
    <unused1097>
    1.11
    <unused294>
    1.10
     المعادلات
    1.10
     Ernährung
    1.08
     religión
    1.07
     keuangan
    1.07
    Mkv
    1.06
    <unused2058>
    1.06
    Activations Density 0.188%

    No Known Activations