© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5224
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    8
    0.69
    -
    0.63
     leftmost
    0.57
    9
    0.52
    '
    0.52
    5
    0.51
    4
    0.47
    *
    0.46
     knuckles
    0.45
     naughty
    0.44
    POSITIVE LOGITS
    л
    2.59
    ار
    2.49
    dra
    2.48
     Ді
    2.46
    اري
    2.45
    т
    2.45
    πο
    2.44
    ла
    2.44
    клады
    2.44
    тре
    2.43
    Activations Density 0.009%

    No Known Activations