© 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. 100332
    Prev
    Next
    INDEX
    Explanations

    ordinal day followed by month

    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
    spyOn
    -1.45
     prodej
    -1.36
    comes
    -1.35
     przód
    -1.33
    了下来
    -1.33
    0
    -1.27
    which
    -1.27
    iramente
    -1.26
     zwi
    -1.26
    vlád
    -1.25
    POSITIVE LOGITS
     the
    1.29
     betek
    1.26
    ))$_
    1.23
     antena
    1.22
    ञ
    1.17
     hôtel
    1.15
    銆
    1.14
    [
    1.10
     luto
    1.10
     Souha
    1.10
    Activations Density 0.056%

    No Known Activations