© 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. 34-GEMMASCOPE-RES-131K
    7. 32950
    Prev
    Next
    INDEX
    Explanations

    NFS speed BioConnect model

    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_34/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
    ASTRO
    -0.69
    ૧
    -0.69
     automation
    -0.67
     نیروهای
    -0.66
    Authorize
    -0.66
     residencial
    -0.64
    лица
    -0.64
    وث
    -0.64
    Women
    -0.64
    ticias
    -0.64
    POSITIVE LOGITS
    Underground
    0.81
     blacklist
    0.81
     Underground
    0.79
    པ
    0.77
    πο
    0.77
     NFS
    0.75
     protege
    0.73
    cepts
    0.70
    Forbidden
    0.70
     Carbon
    0.69
    Activations Density 0.028%

    No Known Activations