© 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. 129309
    Prev
    Next
    INDEX
    Explanations

    quality descriptions

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

    states or roles

    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
     depictions
    0.53
     дочери
    0.51
     موم
    0.50
     vincul
    0.50
     frères
    0.49
     discut
    0.48
     microp
    0.48
     ሥ
    0.47
     ఓ
    0.46
     местах
    0.46
    POSITIVE LOGITS
     Metrics
    0.52
     Management
    0.46
     Gauge
    0.45
    gauge
    0.43
     Caught
    0.43
    signal
    0.43
     Market
    0.42
     MANAGEMENT
    0.42
    <0xAB>
    0.42
    progress
    0.41
    Activations Density 0.000%

    No Known Activations