© 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. 227926
    Prev
    Next
    INDEX
    Explanations

    describing actions following certain words

    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
    मैन
    0.46
     voyez
    0.45
     réduire
    0.45
     nakon
    0.43
     صلى
    0.43
    т
    0.43
     služ
    0.43
     tiszt
    0.43
     Ferg
    0.42
     cé
    0.42
    POSITIVE LOGITS
    ONY
    0.46
    ,\,\,\,\
    0.45
    prochen
    0.45
    EOS
    0.44
    𝗢
    0.44
     cooperate
    0.44
    
    0.44
     lecture
    0.43
    icidal
    0.43
     పాఠ
    0.42
    Activations Density 0.000%

    No Known Activations