© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13894
    Prev
    Next
    INDEX
    Explanations

    born followed by date

    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
     will
    -1.47
    th
    -1.38
     if
    -1.37
    s
    -1.34
    u
    -1.30
    sa
    -1.30
    first
    -1.30
     cristian
    -1.26
     "
    -1.25
    mi
    -1.25
    POSITIVE LOGITS
    irical
    1.30
     protegida
    1.20
    гля
    1.19
    bàn
    1.19
    ższe
    1.15
    ghurt
    1.15
    bsen
    1.14
    peño
    1.13
    Filmo
    1.13
    verbs
    1.13
    Activations Density 0.199%

    No Known Activations