© 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. 236864
    Prev
    Next
    INDEX
    Explanations

    designed by, experience using

    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
    셉
    0.44
     erythro
    0.44
     '';
    0.43
    Neue
    0.43
     BIS
    0.42
     별
    0.41
     neues
    0.41
    CHINA
    0.41
     CHINA
    0.41
     kaleidos
    0.41
    POSITIVE LOGITS
     कॉंग्रेस
    0.55
    ضی
    0.52
     electromagnetic
    0.48
    ceramic
    0.48
    frigerator
    0.46
    ५
    0.46
     electromagnet
    0.46
    avy
    0.45
    covery
    0.45
     présent
    0.45
    Activations Density 0.001%

    No Known Activations