© 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. 22-GEMMASCOPE-RES-131K
    7. 10859
    Prev
    Next
    INDEX
    Explanations

    forward information or issues

    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
    -1.70
     hacer
    -1.59
    </b>
    -1.58
    骓
    -1.45
    </h1>
    -1.45
     If
    -1.42
    d
    -1.40
     at
    -1.40
     that
    -1.39
     on
    -1.38
    POSITIVE LOGITS
    臜
    1.71
     девя
    1.50
     répand
    1.42
    primarily
    1.41
    咙
    1.38
     religiosos
    1.36
    depending
    1.34
     praticamente
    1.34
    neither
    1.31
     izquier
    1.30
    Activations Density 0.030%

    No Known Activations