© 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. 258168
    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
    ಾಗಿತ್ತು
    0.50
    of
    0.50
    ।
    0.49
    кта
    0.47
    ба
    0.46
    。
    0.45
    а
    0.44
    របស់
    0.44
    о
    0.44
    ider
    0.43
    POSITIVE LOGITS
     dokument
    0.47
     innocuous
    0.44
     axons
    0.43
     deception
    0.42
     assail
    0.41
     expedit
    0.41
     precludes
    0.41
     leurs
    0.40
     undeni
    0.40
     deceptive
    0.40
    Activations Density 0.007%

    No Known Activations