© 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. 10-GEMMASCOPE-RES-131K
    7. 100061
    Prev
    Next
    INDEX
    Explanations

    print followed by what to print

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

    the verb "print" in technical or instructional contexts, particularly in programming and document-related discussions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    "
    -2.50
    ☫
    -2.14
     I
    -2.09
    ⸥
    -2.06
     लेकिन
    -2.06
    \
    -1.92
     /
    -1.89
    亵
    -1.87
    ご了承
    -1.80
    ’
    -1.78
    POSITIVE LOGITS
    猡
    2.50
    
    2.47
    इटम
    2.39
    ayage
    2.38
     laterales
    2.30
    derdag
    2.09
    囌
    2.08
    夀
    1.97
    嫗
    1.93
     cejas
    1.91
    Activations Density 0.050%

    No Known Activations