© 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. 255978
    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
     temperatur
    0.49
     Year
    0.48
     preceding
    0.46
     ador
    0.46
     traversing
    0.45
     pairs
    0.44
     tables
    0.44
    .");
    0.44
     surround
    0.43
     Temperatur
    0.42
    POSITIVE LOGITS
    EXE
    0.57
    я
    0.54
    Fraud
    0.52
    ISA
    0.52
    YA
    0.49
    Banco
    0.49
    DISK
    0.49
    NHK
    0.48
    જાર
    0.48
    Prevent
    0.48
    Activations Density 0.000%

    No Known Activations