© 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. 10-GEMMASCOPE-RES-131K
    7. 40373
    Prev
    Next
    INDEX
    Explanations

    string interpolation with variables

    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
     or
    -2.70
     also
    -2.28
     as
    -2.16
     by
    -1.96
    or
    -1.88
     through
    -1.84
     used
    -1.78
     received
    -1.78
     first
    -1.68
     believes
    -1.66
    POSITIVE LOGITS
    翃
    1.88
     ſont
    1.70
     organisme
    1.68
    倻
    1.67
    锨
    1.64
     alarme
    1.64
     rapidement
    1.64
    ⵌ
    1.63
    鸨
    1.63
     apropri
    1.63
    Activations Density 0.006%

    No Known Activations