© 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. 111974
    Prev
    Next
    INDEX
    Explanations

    Pakistani troops

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

    market analysis and trading

    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
    Ratio
    0.48
    UserNotification
    0.47
    ተ
    0.47
    Seite
    0.46
     actief
    0.46
    JAN
    0.46
    墳
    0.45
    焓
    0.44
    Distrib
    0.44
    Jan
    0.43
    POSITIVE LOGITS
     seventy
    0.50
     fios
    0.47
     साउथ
    0.46
     Seventy
    0.45
     portuguesa
    0.45
     conflicting
    0.45
     privy
    0.43
     क्रिएट
    0.43
     on
    0.42
    ores
    0.42
    Activations Density 0.001%

    No Known Activations