© 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. 248665
    Prev
    Next
    INDEX
    Explanations

    context words

    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
    ور
    0.50
     passando
    0.50
    ه
    0.50
    س
    0.49
    米
    0.47
     Spencer
    0.47
     Donc
    0.46
     ordinary
    0.45
    ї
    0.45
    伊
    0.45
    POSITIVE LOGITS
    fieldContext
    0.55
    CONTEXT
    0.50
    ContextHeader
    0.50
     '</
    0.50
    缄
    0.49
     পড়েন
    0.48
    yman
    0.47
     контек
    0.45
     मुक्ति
    0.45
    cookbook
    0.44
    Activations Density 0.001%

    No Known Activations