© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1573
    Prev
    Next
    INDEX
    Explanations

    mailto:

    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_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
     promotes
    -2.36
     notable
    -2.27
    </b>
    -2.17
    ساء
    -2.14
     has
    -2.09
    jenigen
    -2.09
     resolute
    -2.08
     burgeoning
    -2.05
     facilitates
    -2.05
     serves
    -2.03
    POSITIVE LOGITS
     the
    2.83
    “
    2.72
    ientras
    2.61
     zoude
    2.61
     spann
    2.58
    錞
    2.55
    >
    2.52
    provides
    2.47
    *
    2.47
     EIGHT
    2.45
    Activations Density 0.006%

    No Known Activations