© 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. 114081
    Prev
    Next
    INDEX
    Explanations

    company does, gas temperature, he left

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

    contrast and exceptions

    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
     一个
    0.54
    <0x04>
    0.48
    阳
    0.47
    轮
    0.45
    [:-
    0.44
    (*(
    0.44
     አማ
    0.44
    篮
    0.44
    蝰
    0.44
    小编
    0.44
    POSITIVE LOGITS
    trusive
    0.47
     inexplicable
    0.44
     celeb
    0.43
     kajian
    0.42
    brado
    0.42
     exista
    0.42
     acaba
    0.41
     afflicted
    0.41
     adversity
    0.41
     acost
    0.40
    Activations Density 0.001%

    No Known Activations