© 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. 1438
    Prev
    Next
    INDEX
    Explanations

    time to double or decay

    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
    getFocusAreas
    0.49
     fortalecer
    0.45
     ombil
    0.44
     insertions
    0.44
    菜单
    0.43
    蒌
    0.43
     coordinadora
    0.42
     vín
    0.42
    isVideoRecording
    0.42
     ننوت
    0.41
    POSITIVE LOGITS
     approximate
    0.59
    approx
    0.55
    Approx
    0.53
     approximately
    0.52
     Approximate
    0.48
     approx
    0.48
     ≈
    0.47
     aprox
    0.47
     doubling
    0.46
     roughly
    0.44
    Activations Density 0.001%

    No Known Activations