© 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. 34398
    Prev
    Next
    INDEX
    Explanations

    percentages and counts

    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
    ):
    -1.09
     vacas
    -1.09
    orneys
    -1.05
    ството
    -1.05
    uação
    -1.03
     cuchillo
    -1.03
     víctima
    -1.02
    中國
    -1.02
    ();
    -1.02
    InSection
    -1.00
    POSITIVE LOGITS
     according
    1.51
     statistics
    1.45
     statistic
    1.41
     recent
    1.37
     compared
    1.35
     this
    1.32
     data
    1.27
     latest
    1.21
     estimates
    1.11
     last
    1.08
    Activations Density 0.057%

    No Known Activations