© 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. 25916
    Prev
    Next
    INDEX
    Explanations

    Expense Ratio, Metro Line

    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
     depresión
    0.57
    лександр
    0.49
     depressed
    0.48
     эмоциона
    0.48
     состоит
    0.47
     इंफॉर्मेशन
    0.47
     poesía
    0.46
    뽕
    0.46
    Emotional
    0.45
    Después
    0.44
    POSITIVE LOGITS
     pak
    0.47
     hauling
    0.46
     vina
    0.45
    ស់
    0.45
    annon
    0.45
     mites
    0.44
     Mits
    0.44
     භාවිත
    0.43
    apis
    0.43
     imports
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.