© 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. 237616
    Prev
    Next
    INDEX
    Explanations

    your expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    B
    0.45
     Phillips
    0.44
     पढ़ाई
    0.42
    એ
    0.42
    贵
    0.42
     Rider
    0.41
    🌹
    0.41
    💡
    0.41
     tế
    0.40
     συνέχεια
    0.40
    POSITIVE LOGITS
    茣
    0.52
     litoral
    0.47
     شدہ
    0.47
     Labrenzia
    0.47
    xyplot
    0.47
    DialogWhen
    0.47
     komponen
    0.45
    هره
    0.45
     curviliné
    0.45
     mulch
    0.45
    Activations Density 0.001%

    No Known Activations