© 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. 233693
    Prev
    Next
    INDEX
    Explanations

    metal bread or produce

    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
    民间
    0.49
    钚
    0.48
    備
    0.48
    youtube
    0.47
    쁜
    0.46
     Punishment
    0.46
     இந்தியா
    0.45
    state
    0.44
    芡
    0.44
     அக
    0.44
    POSITIVE LOGITS
     estimators
    0.51
     linkages
    0.47
    始めた
    0.47
     issu
    0.46
     licences
    0.46
     suppliers
    0.45
     ağırl
    0.44
     ecosystems
    0.43
     gradu
    0.43
     specimen
    0.43
    Activations Density 0.001%

    No Known Activations