© 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. 158927
    Prev
    Next
    INDEX
    Explanations

    chronic asthma, flourishing, texts, visiting, child's school, knowing now, gears, if, higher pitch, rolling

    np_acts-logits-general · gemini-2.5-flash-lite

    technical terms, places, and conversations

    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
     COUNTRY
    0.49
    UA
    0.47
     BODY
    0.47
    উ
    0.46
     protezione
    0.46
    批准
    0.44
     posizione
    0.43
    ру
    0.42
    config
    0.42
    ↵↵↵↵↵
    0.41
    POSITIVE LOGITS
     всегда
    0.47
     lackluster
    0.44
     وړاند
    0.44
    ıml
    0.44
     വന്ന
    0.44
     عالم
    0.44
     wszel
    0.43
     वोल्ट
    0.42
     volatility
    0.41
    Chev
    0.41
    Activations Density 0.000%

    No Known Activations