© 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. 161120
    Prev
    Next
    INDEX
    Explanations

    person birth month

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

    SQL command fragments

    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
     agricultura
    0.52
    मिथ
    0.52
    ೭
    0.48
    㠻
    0.48
     பரப்பு
    0.46
    慗
    0.46
    ૫
    0.46
    мын
    0.45
    ષ
    0.45
    ๗
    0.45
    POSITIVE LOGITS
     ছেলে
    0.43
     brin
    0.40
    labelled
    0.40
    一大
    0.38
     labelled
    0.38
     watts
    0.37
     Node
    0.37
     Watts
    0.37
     Bram
    0.37
     subspaces
    0.36
    Activations Density 0.001%

    No Known Activations