© 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. 244106
    Prev
    Next
    INDEX
    Explanations

    exudation, optimization, synthesis

    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
    Interest
    0.53
    belief
    0.51
     później
    0.50
    onError
    0.50
     $:
    0.48
    parcel
    0.47
    boek
    0.47
    향
    0.46
    playing
    0.45
    차
    0.45
    POSITIVE LOGITS
     exud
    0.52
     micrographs
    0.50
     optimization
    0.48
     baker
    0.48
     juxtaposition
    0.47
     categorization
    0.47
     curvil
    0.46
     mélange
    0.46
     latex
    0.46
     synthesis
    0.46
    Activations Density 0.000%

    No Known Activations