© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 256964
    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
     ресур
    0.45
     توی
    0.45
     Utilization
    0.44
    휙
    0.43
     Ressources
    0.43
    篁
    0.43
     decedent
    0.42
     Etiam
    0.42
     varit
    0.42
     Всё
    0.42
    POSITIVE LOGITS
    ة
    0.51
    fract
    0.50
    fromj
    0.46
    prevent
    0.46
    oxidation
    0.46
    پوینت
    0.45
    他和
    0.45
    isometric
    0.44
     oil
    0.44
    éct
    0.44
    Activations Density 0.001%

    No Known Activations