© 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. 19275
    Prev
    Next
    INDEX
    Explanations

    locations and regions

    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
    <unused2104>
    0.96
    <unused404>
    0.91
    <unused689>
    0.77
    <unused2133>
    0.77
    <unused1151>
    0.77
    roskop
    0.74
    <unused1865>
    0.73
    <unused502>
    0.72
    <unused576>
    0.72
    <unused2056>
    0.71
    POSITIVE LOGITS
     Queensland
    1.41
     Manitoba
    1.41
     Kerala
    1.38
    Queensland
    1.35
     NZ
    1.32
     NSW
    1.31
     kerala
    1.31
    NSW
    1.30
     Haryana
    1.29
     Punjab
    1.26
    Activations Density 0.282%

    No Known Activations