© 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. 22-GEMMASCOPE-RES-131K
    7. 33511
    Prev
    Next
    INDEX
    Explanations

    United States

    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_22/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
     varias
    -1.05
     after
    -1.00
     to
    -0.90
    -
    -0.86
     all
    -0.86
    ̾
    -0.85
     все
    -0.85
     if
    -0.85
     or
    -0.84
     souhaite
    -0.83
    POSITIVE LOGITS
     both
    3.31
    both
    3.11
     beiden
    2.97
    Both
    2.97
    这两个
    2.94
     दोनों
    2.86
     beide
    2.86
     båda
    2.69
     ambos
    2.61
     Beide
    2.61
    Activations Density 0.050%

    No Known Activations