© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99199
    Prev
    Next
    INDEX
    Explanations

    citation markers

    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
     hundreds
    -1.23
     hundred
    -0.97
     ۱
    -0.96
     century
    -0.90
     cientos
    -0.89
    Hundreds
    -0.89
     Hundreds
    -0.88
     you
    -0.85
     CONSIDERATIONS
    -0.84
     都
    -0.79
    POSITIVE LOGITS
     our
    1.26
    Titled
    0.99
    我們的
    0.89
     nineteen
    0.88
     eighteen
    0.87
     seventeen
    0.86
     bizim
    0.86
     élu
    0.85
     naše
    0.83
     våra
    0.82
    Activations Density 0.003%

    No Known Activations