© 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. 182420
    Prev
    Next
    INDEX
    Explanations

    delicate language

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

    prefer to

    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
    Ciudad
    0.55
    Tarjeta
    0.52
    楽しく
    0.51
    德
    0.50
    )।
    0.49
    њем
    0.49
    ELSE
    0.48
    一笑
    0.47
    嘏
    0.47
    OSED
    0.47
    POSITIVE LOGITS
     Camera
    0.54
     children
    0.50
     American
    0.49
    ror
    0.48
     Cabinet
    0.48
    computer
    0.47
     theory
    0.47
    ras
    0.47
     computer
    0.46
     Mechanical
    0.46
    Activations Density 0.000%

    No Known Activations