© 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. 123855
    Prev
    Next
    INDEX
    Explanations

    routes after nouns

    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
     that
    -2.02
     from
    -1.67
     pueden
    -1.59
     tiempo
    -1.48
     who
    -1.45
     puede
    -1.45
     hacen
    -1.44
     though
    -1.42
     ampio
    -1.40
     selalu
    -1.39
    POSITIVE LOGITS
     şi
    1.68
     Entreprises
    1.47
     vinyle
    1.46
     extraordinaire
    1.44
    /
    1.43
    -
    1.43
     \&
    1.41
     Cabrio
    1.38
     Ciné
    1.38
    стях
    1.38
    Activations Density 0.035%

    No Known Activations