© 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. 41623
    Prev
    Next
    INDEX
    Explanations

    examples and illustrative phrases

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

    examples or listing

    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
     ৬
    0.47
     Enhance
    0.45
     BSE
    0.40
     XRD
    0.39
    6
    0.38
     AMD
    0.38
     ECB
    0.38
     IPCC
    0.38
     ৮
    0.37
     EEG
    0.36
    POSITIVE LOGITS
    例えば
    0.59
     예를
    0.56
    たとえば
    0.56
     Например
    0.51
    например
    0.51
    どのような
    0.51
     مثلا
    0.50
    某
    0.49
     например
    0.48
    什么样的
    0.47
    Activations Density 0.012%

    No Known Activations