© 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. 191326
    Prev
    Next
    INDEX
    Explanations

    image/gif and drawing

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

    definitions or concepts

    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
     eh
    0.57
     lege
    0.46
     Sao
    0.45
     ter
    0.45
     Will
    0.44
     '
    0.44
    に入
    0.44
     Í
    0.43
     Col
    0.43
     penultimate
    0.43
    POSITIVE LOGITS
    נ
    0.57
    Kaynakça
    0.49
    ्रेसेस
    0.48
    𒊹
    0.48
    Ɩ
    0.48
     रिश्
    0.47
    极致
    0.47
    ালি
    0.47
    వారి
    0.47
    লাইট
    0.47
    Activations Density 0.000%

    No Known Activations