© 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. 58867
    Prev
    Next
    INDEX
    Explanations

    holidays and dates

    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
     in
    -2.06
     with
    -1.87
     although
    -1.76
     on
    -1.61
     through
    -1.59
     while
    -1.59
     as
    -1.56
     by
    -1.51
     if
    -1.51
     despite
    -1.38
    POSITIVE LOGITS
     such
    1.55
    
    1.54
     ſou
    1.39
    pousada
    1.38
     groote
    1.33
    zzet
    1.30
     його
    1.30
    茕
    1.30
    orul
    1.29
     子ども
    1.29
    Activations Density 0.032%

    No Known Activations