© 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. 22-GEMMASCOPE-RES-131K
    7. 16123
    Prev
    Next
    INDEX
    Explanations

    months 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_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
    licitations
    -1.56
    🪛
    -1.55
     mwenye
    -1.52
     interesses
    -1.52
     viennent
    -1.48
     começo
    -1.46
     voltaje
    -1.45
    arised
    -1.45
    ěry
    -1.42
     variaciones
    -1.42
    POSITIVE LOGITS
     or
    1.86
     during
    1.79
     February
    1.72
     if
    1.68
     November
    1.63
     July
    1.59
     October
    1.56
     December
    1.52
     should
    1.52
     use
    1.52
    Activations Density 0.017%

    No Known Activations