© 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. 249640
    Prev
    Next
    INDEX
    Explanations

    Z coordinate and temperature

    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
     invariance
    0.47
     ぐらい
    0.46
    朧
    0.45
    ራት
    0.45
    িনীত
    0.44
     Deformation
    0.44
     объекты
    0.42
    FBSDKInternal
    0.42
     maximally
    0.42
    ){}^
    0.41
    POSITIVE LOGITS
    edores
    0.50
    wa
    0.46
     irland
    0.45
     gangs
    0.43
     calor
    0.43
     kor
    0.42
     causas
    0.42
     corridor
    0.42
    كل
    0.41
     adolescente
    0.41
    Activations Density 0.002%

    No Known Activations