© 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. 203499
    Prev
    Next
    INDEX
    Explanations

    great things, illustrations

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

    uranium atoms, bull quickly, remove punctuation

    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
    主に
    0.54
    診療
    0.51
    Ე
    0.50
    environments
    0.49
    rural
    0.49
    ksiyon
    0.49
     वाणी
    0.47
    mainly
    0.47
     주로
    0.47
    resourceUrl
    0.46
    POSITIVE LOGITS
     percentage
    0.59
     $
    0.57
     increase
    0.55
    0.55
     Google
    0.54
     improve
    0.52
     @
    0.52
     percent
    0.49
     pope
    0.48
     (
    0.47
    Activations Density 0.000%

    No Known Activations