© 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. 39734
    Prev
    Next
    INDEX
    Explanations

    claus plant, largest screen, long trip, call strike

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

    LLM model, category, division

    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
     _
    0.53
    Gc
    0.47
     Mrs
    0.46
    Notre
    0.46
    .-
    0.45
     -!
    0.45
    onat
    0.45
     Das
    0.44
    .,
    0.44
     Kaplan
    0.44
    POSITIVE LOGITS
    ческие
    0.53
     besitzen
    0.53
     શા
    0.52
     ज़्यादा
    0.52
    presentasikan
    0.52
    াচ্ছে
    0.51
    েরিক
    0.50
    ਪ
    0.50
     afect
    0.50
    的表现
    0.50
    Activations Density 0.000%

    No Known Activations