© 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. 14236
    Prev
    Next
    INDEX
    Explanations

    website urls and paths

    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
    Фран
    1.06
    🌥
    0.98
     Франции
    0.95
    <unused111>
    0.95
    Frankreich
    0.93
    bedingt
    0.93
    𝙣
    0.93
    ễm
    0.93
    界面
    0.93
    ANZ
    0.93
    POSITIVE LOGITS
     more
    0.78
    0.75
     ch
    0.74
     적
    0.69
     Un
    0.69
     un
    0.67
     Ch
    0.67
     Z
    0.67
     g
    0.65
    :
    0.64
    Activations Density 0.001%

    No Known Activations