© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64570
    Prev
    Next
    INDEX
    Explanations

    statements of fact or description

    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
     even
    -2.33
     either
    -2.23
     навіть
    -1.97
     also
    -1.88
     даже
    -1.80
     however
    -1.80
     però
    -1.76
    不仅
    -1.71
     bahkan
    -1.63
    either
    -1.63
    POSITIVE LOGITS
    确实
    1.60
     may
    1.56
     misschien
    1.45
    Certainly
    1.44
     technically
    1.34
     certamente
    1.32
     inicialmente
    1.30
    的确
    1.29
    Initially
    1.29
    şek
    1.28
    Activations Density 0.125%

    No Known Activations