© 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. 200373
    Prev
    Next
    INDEX
    Explanations

    recognizing "every place"

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

    vibe check and funding development

    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
    =":
    0.49
    )}$.
    0.48
    Ups
    0.47
    pk
    0.45
    点
    0.44
     Ups
    0.43
     हटाया
    0.43
     harmonica
    0.42
    ሉም
    0.42
    \}=\
    0.42
    POSITIVE LOGITS
     आध्यात्मिक
    0.49
     közvet
    0.46
     ideales
    0.46
     carreteras
    0.46
    ührt
    0.46
     artes
    0.46
    ihad
    0.45
     nyata
    0.45
     környez
    0.45
     intravenously
    0.44
    Activations Density 0.001%

    No Known Activations