© 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. 29074
    Prev
    Next
    INDEX
    Explanations

    auto-completion

    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
     colocado
    -1.45
    extrémité
    -1.41
     powinny
    -1.35
     montado
    -1.34
     permitido
    -1.34
     vinculado
    -1.34
    épaisseur
    -1.33
    卝
    -1.30
    entraînement
    -1.30
    âme
    -1.29
    POSITIVE LOGITS
     the
    1.59
     Many
    1.44
     any
    1.44
    after
    1.40
     Several
    1.38
     Eight
    1.37
     Currently
    1.37
     However
    1.35
     their
    1.34
    …..
    1.33
    Activations Density 0.040%

    No Known Activations