© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198652
    Prev
    Next
    INDEX
    Explanations

    cake I

    np_acts-logits-general · gemini-2.5-flash-lite

    structured lists or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vám
    0.50
     مبلغ
    0.50
     neue
    0.50
     deine
    0.47
     bạn
    0.46
     stylish
    0.46
     உங்கள்
    0.45
     你
    0.45
     negozi
    0.45
     spez
    0.45
    POSITIVE LOGITS
    鮋
    0.50
     воспа
    0.45
     분포
    0.43
     antagonism
    0.42
     discer
    0.42
    करना
    0.41
    챔
    0.41
     Variation
    0.40
     incontinence
    0.40
     THEY
    0.40
    Activations Density 0.001%

    No Known Activations