© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106644
    Prev
    Next
    INDEX
    Explanations

    date and time format specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     штук
    -0.74
     Rah
    -0.73
    abilis
    -0.73
    Rah
    -0.72
     हा
    -0.71
    actus
    -0.70
     foreseeable
    -0.70
     problems
    -0.70
     clásica
    -0.69
    覚
    -0.69
    POSITIVE LOGITS
     '%
    1.12
    ('%
    1.09
    ("%
    1.05
     "%
    0.97
     %
    0.92
     \"%
    0.91
    =%
    0.90
    /%
    0.90
     (%
    0.89
    (%
    0.86
    Activations Density 0.018%

    No Known Activations