© 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. 165201
    Prev
    Next
    INDEX
    Explanations

    size or quantity

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

    chemical formulas and structures

    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
    یل
    0.49
    েন্স
    0.49
    ح
    0.48
     Reduction
    0.46
    لر
    0.46
     Diamonds
    0.46
     Professional
    0.46
     Physical
    0.44
     Certified
    0.44
    ปลอดภัย
    0.43
    POSITIVE LOGITS
     ఇప్పటికే
    0.49
    Greet
    0.48
    inities
    0.48
    ейчас
    0.47
    judicial
    0.47
    }~\
    0.46
    Roaming
    0.46
    {*
    0.46
     интегра
    0.46
    uh
    0.45
    Activations Density 0.001%

    No Known Activations