© 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. 196695
    Prev
    Next
    INDEX
    Explanations

    pattern recognition

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

    swallow, CPU, feels, conclusions, tuple

    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
     Electronic
    0.48
     Brought
    0.46
     *
    0.45
     Ins
    0.44
     persistently
    0.44
     brought
    0.43
     Checked
    0.43
     [[
    0.43
     hadn
    0.43
     CAT
    0.42
    POSITIVE LOGITS
    ergewöhn
    0.50
    tevõ
    0.50
     emociones
    0.48
    aging
    0.47
    iare
    0.46
    nú
    0.45
    ធាតុ
    0.45
    tanh
    0.44
    recognition
    0.44
    anzas
    0.44
    Activations Density 0.001%

    No Known Activations