© 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. 129351
    Prev
    Next
    INDEX
    Explanations

    peaceful purpose, low return, national theatrical

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

    project terms and descriptions

    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
    ，
    0.47
     balls
    0.43
     ，
    0.42
     EQ
    0.41
     airflow
    0.41
    exo
    0.40
     BG
    0.39
     диа
    0.39
    வுக்கு
    0.39
    েবে
    0.38
    POSITIVE LOGITS
    欱
    0.46
     jamás
    0.46
    遉
    0.46
    န်
    0.44
     nových
    0.44
    QtWidgets
    0.44
    smallest
    0.43
    க்கணக்கான
    0.43
    桅
    0.43
    茟
    0.43
    Activations Density 0.000%

    No Known Activations