© 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. 197030
    Prev
    Next
    INDEX
    Explanations

    stages of learning

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

    specific nouns

    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
     처음
    0.59
     승
    0.57
     selection
    0.55
     submar
    0.50
     bottleneck
    0.50
     항
    0.50
     받을
    0.50
     선
    0.49
    rang
    0.48
     받
    0.48
    POSITIVE LOGITS
    Hyundai
    0.46
     Augustus
    0.45
    AIN
    0.44
    Listen
    0.43
    Clusters
    0.43
     Stages
    0.42
    েন্দু
    0.42
     প্রাদেশিক
    0.42
    你
    0.42
     Flowering
    0.42
    Activations Density 0.000%

    No Known Activations