© 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. 72894
    Prev
    Next
    INDEX
    Explanations

    dates and days of the week

    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
    prek
    -0.95
     ответствен
    -0.86
    ：“……”
    -0.86
     vannak
    -0.86
    temps
    -0.86
    //'
    -0.85
     fontos
    -0.85
     Boots
    -0.84
    /*:
    -0.84
     waż
    -0.82
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.96
     Tuesday
    0.96
     sultry
    0.94
    íts
    0.84
    റ
    0.83
    σης
    0.82
     Friday
    0.82
     Saturday
    0.81
    cracy
    0.81
    oughby
    0.81
    Activations Density 0.149%

    No Known Activations