© 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. 236379
    Prev
    Next
    INDEX
    Explanations

    ASAP

    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
    状態で
    0.46
     previs
    0.43
    hmC
    0.41
    趕
    0.41
     psico
    0.40
    上で
    0.40
    軌
    0.40
    つつ
    0.40
    恩
    0.40
     linings
    0.40
    POSITIVE LOGITS
     शाळे
    0.44
     Useful
    0.44
     সম্পদের
    0.43
    Fruit
    0.43
     उत्पत्ति
    0.43
     సం
    0.42
     Explore
    0.42
    Scopes
    0.42
    ്‍
    0.41
    ის
    0.41
    Activations Density 0.000%

    No Known Activations