© 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. 260798
    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
    acc
    0.52
     Джон
    0.52
     किड्स
    0.49
    켄
    0.46
    日常
    0.46
     क्रिप्ट
    0.46
     कैंड
    0.46
    appoint
    0.46
    rok
    0.45
    grand
    0.45
    POSITIVE LOGITS
     previa
    0.44
     exfoli
    0.44
     tenter
    0.42
     hyaluronic
    0.42
     percobaan
    0.42
     ethylene
    0.42
     anteced
    0.41
    τερα
    0.41
     aort
    0.41
    ;<
    0.41
    Activations Density 0.001%

    No Known Activations