© 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. 28089
    Prev
    Next
    INDEX
    Explanations

    figures, names, or descriptions

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

    lacks or seeking other

    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
     leftWheel
    0.49
     beaded
    0.46
     fillets
    0.46
     tumbled
    0.46
     overtook
    0.46
     draped
    0.45
     necklace
    0.43
    ኞ
    0.43
     progressively
    0.42
     Mentre
    0.42
    POSITIVE LOGITS
    in
    0.54
    امج
    0.47
     Reza
    0.47
    n
    0.47
    vien
    0.46
    iv
    0.46
     imponer
    0.46
    ing
    0.45
    h
    0.45
    official
    0.45
    Activations Density 0.001%

    No Known Activations