© 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. 147695
    Prev
    Next
    INDEX
    Explanations

    lists of things or places

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

    Signs and qualifications

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Ì
    0.47
    >[
    0.46
    ικού
    0.46
    Ỉ
    0.45
     đổi
    0.44
     crescita
    0.44
    ỉ
    0.41
    Ƹ
    0.41
    сної
    0.40
     I
    0.39
    POSITIVE LOGITS
     erred
    0.57
     puzzled
    0.55
     signaler
    0.48
    㝢
    0.47
     عن
    0.46
    დილ
    0.46
     効果
    0.46
     fidget
    0.46
     puzzling
    0.46
    챙
    0.46
    Activations Density 0.001%

    No Known Activations