© 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. 45800
    Prev
    Next
    INDEX
    Explanations

    a great, good luck, deep within

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

    calorie burns, finding, capture, rates

    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
     संयंत्र
    0.48
     于
    0.43
    ಾಯಕ
    0.42
     Polymer
    0.41
     शिफ्ट
    0.41
     सामने
    0.41
     প্রশংস
    0.41
    ulins
    0.40
     conveying
    0.40
     ච
    0.40
    POSITIVE LOGITS
    civil
    0.49
    IGE
    0.47
    HEAT
    0.47
    C
    0.45
    African
    0.43
    GÁ
    0.43
    data
    0.43
    ZO
    0.43
    спе
    0.43
    Civil
    0.43
    Activations Density 0.000%

    No Known Activations