© 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. 22-GEMMASCOPE-RES-131K
    7. 34731
    Prev
    Next
    INDEX
    Explanations

    months of the year

    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_22/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
     ২০১
    -1.90
    ૉ
    -1.49
     recently
    -1.43
     현재
    -1.40
     currently
    -1.39
     newest
    -1.38
     recentemente
    -1.36
     maintenant
    -1.34
    怎麼辦
    -1.34
     vanil
    -1.34
    POSITIVE LOGITS
     after
    1.82
     without
    1.52
     by
    1.43
     while
    1.40
     during
    1.37
     fourteen
    1.32
     religiosas
    1.30
     guantes
    1.27
     shortly
    1.25
     religious
    1.23
    Activations Density 0.087%

    No Known Activations