© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 254042
    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
    ազմ
    0.50
    leş
    0.50
     mellem
    0.49
    ੱ
    0.48
     ነው
    0.48
     ناح
    0.48
    ੱਕ
    0.47
    laş
    0.47
     ਟ
    0.47
    jän
    0.46
    POSITIVE LOGITS
     Priorities
    0.47
     Kippur
    0.47
     Blackhawks
    0.47
    "]));
    0.45
     *_
    0.44
     Interests
    0.44
     Ceiling
    0.43
     Yvonne
    0.42
    </h3>
    0.42
     Óscar
    0.41
    Activations Density 0.002%

    No Known Activations