© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 28
    Prev
    Next
    INDEX
    Explanations

    Salmani, Kulkarni, Kamado

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    <unused1350>
    0.79
    <unused1294>
    0.79
    <unused1475>
    0.77
    <unused1339>
    0.74
    <unused1349>
    0.73
    <unused1300>
    0.73
    <unused1385>
    0.72
    <start_of_turn>
    0.71
    㣙
    0.71
    鿢
    0.71
    POSITIVE LOGITS
    ’
    0.76
     brothers
    0.74
    -
    0.70
    _
    0.67
    online
    0.66
     adlı
    0.65
    ian
    0.62
     spp
    0.61
    /
    0.61
    '
    0.60
    Activations Density 5.997%

    No Known Activations