© 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. 247257
    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
    ↵
    0.31
    G
    0.30
    1
    0.28
    С
    0.27
    <strong>
    0.27
    ↵↵
    0.26
    e
    0.26
    Q
    0.26
    the
    0.26
    E
    0.26
    POSITIVE LOGITS
     instaur
    0.25
     annih
    0.24
     ennemis
    0.23
     cicat
    0.23
    ټبال
    0.23
    reflectionMap
    0.23
     sillons
    0.23
     funer
    0.22
    gramModel
    0.22
     pathogenesis
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.