© 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. 3863
    Prev
    Next
    INDEX
    Explanations

    Iijima, ima

    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
    ↵
    -2.73
    ,”
    -2.73
     Gedanke
    -2.55
     of
    -2.53
    ↵↵
    -2.45
     judíos
    -2.42
    \
    -2.36
     Verbrechen
    -2.30
     utilizing
    -2.27
     verschied
    -2.22
    POSITIVE LOGITS
    ima
    3.20
    </h1>
    2.67
    is
    2.55
    ili
    2.52
    aaaa
    2.42
    ir
    2.41
    e
    2.41
    </strong>
    2.31
    呔
    2.23
    y
    2.22
    Activations Density 0.006%

    No Known Activations