© 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. 30532
    Prev
    Next
    INDEX
    Explanations

    code documentation and data structures

    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
     patiently
    -0.82
     compila
    -0.81
    енные
    -0.77
    \|_{\
    -0.77
     tirantes
    -0.76
     бассе
    -0.75
     工
    -0.73
     galinha
    -0.73
    strlen
    -0.73
     groupName
    -0.73
    POSITIVE LOGITS
     is
    1.10
     can
    0.88
     ayudará
    0.86
    韌
    0.85
    ovým
    0.85
    -------
    0.84
     Алексей
    0.82
     hierv
    0.80
    Synth
    0.79
     Ebenso
    0.78
    Activations Density 0.000%

    No Known Activations