© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 83715
    Prev
    Next
    INDEX
    Explanations

    odometer mileage reading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ഡി
    0.46
     ಸಾವಿರ
    0.45
    ರ್ಯ
    0.42
    قار
    0.42
     হিস
    0.39
    mapping
    0.39
    屍
    0.39
    裂
    0.39
    alka
    0.38
    әр
    0.38
    POSITIVE LOGITS
     interior
    0.49
     actual
    0.49
     low
    0.47
     genuine
    0.46
     nostrils
    0.46
     ACTUAL
    0.45
     authentic
    0.44
     authenticity
    0.43
     exemptions
    0.43
     durable
    0.42
    Activations Density 0.002%

    No Known Activations