© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8671
    Prev
    Next
    INDEX
    Explanations

    separators and titles

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ・・・。
    0.64
    揣
    0.63
    小编
    0.60
    രിക്കും
    0.59
    ווה
    0.58
    উন
    0.57
    entery
    0.57
     तस्वी
    0.56
    Đáp
    0.55
     ಮಟ್ಟ
    0.55
    POSITIVE LOGITS
     -
    2.67
     |
    2.60
     –
    2.16
     —
    1.97
     --
    1.91
     \|
    1.91
    ｜
    1.81
     ||
    1.71
     ·
    1.70
     |-
    1.63
    Activations Density 0.114%

    No Known Activations