© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    physical quantities and measurements

    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
    SuppressWarnings
    0.39
    städ
    0.37
    楍
    0.37
    asyarakat
    0.36
     teamTable
    0.36
    ധിപ
    0.36
    тельством
    0.36
     অপরাধ
    0.35
     уйнау
    0.35
     پیسو
    0.34
    POSITIVE LOGITS
     values
    0.61
     measurement
    0.59
     measurements
    0.58
     levels
    0.57
     reduction
    0.55
     calculation
    0.55
     variation
    0.54
    值
    0.54
     distribution
    0.53
     thresholds
    0.53
    Activations Density 0.122%

    No Known Activations