© 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. 227339
    Prev
    Next
    INDEX
    Explanations

    Kodiak, pregnancy, God, grade, 4

    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
     vui
    0.52
     diaz
    0.51
     tere
    0.50
     wast
    0.47
     pectin
    0.47
     mue
    0.46
     devise
    0.46
    ో
    0.45
     refug
    0.44
    蟻
    0.44
    POSITIVE LOGITS
     विधान
    0.49
    phosphorylation
    0.48
    lici
    0.48
    paragraph
    0.48
    gage
    0.47
    ificant
    0.47
    cent
    0.46
    spanish
    0.46
    rapped
    0.46
    lig
    0.45
    Activations Density 0.000%

    No Known Activations