© 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. 119790
    Prev
    Next
    INDEX
    Explanations

    after an initial stage

    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
     particularly
    -1.59
     more
    -1.59
     those
    -1.55
     and
    -1.48
     especially
    -1.45
     also
    -1.45
     Moreover
    -1.44
     or
    -1.43
     because
    -1.41
     inoltre
    -1.39
    POSITIVE LOGITS
     damos
    1.44
     we
    1.37
     usamos
    1.32
     pontu
    1.24
     bén
    1.20
     dési
    1.16
     fournir
    1.16
     scènes
    1.16
     louer
    1.15
    </h4>
    1.14
    Activations Density 0.092%

    No Known Activations