© 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. 6159
    Prev
    Next
    INDEX
    Explanations

    getting into or started

    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
    Data
    0.81
    Current
    0.79
    Being
    0.77
    All
    0.74
    DataItem
    0.69
    Of
    0.69
    [[
    0.69
    Color
    0.67
    DataObject
    0.66
    Y
    0.66
    POSITIVE LOGITS
     rid
    1.65
     bogged
    1.29
     acquainted
    1.26
     married
    1.16
     into
    1.16
     excited
    1.14
     vaccinated
    1.10
     notified
    1.10
     reimbursed
    1.10
     involved
    1.10
    Activations Density 0.050%

    No Known Activations