© 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. 261020
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     allocated
    0.53
    ↵
    0.52
     gun
    0.50
    N
    0.49
     immensely
    0.47
     billions
    0.47
    M
    0.47
     illusion
    0.46
    S
    0.46
     ironically
    0.45
    POSITIVE LOGITS
    苇
    0.50
    essed
    0.49
    зова
    0.46
    стом
    0.46
    thisobject
    0.46
    ходят
    0.46
     北京
    0.46
    ecast
    0.44
    蚱
    0.44
    étaire
    0.44
    Activations Density 0.001%

    No Known Activations