© 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. 34-GEMMASCOPE-RES-131K
    7. 63337
    Prev
    Next
    INDEX
    Explanations

    around the clock

    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_34/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
    pvc
    -0.69
     atualizar
    -0.68
    preorder
    -0.68
     PRT
    -0.66
    ជ
    -0.66
    ธอ
    -0.65
     TPR
    -0.65
    emballage
    -0.65
     хто
    -0.64
     terri
    -0.63
    POSITIVE LOGITS
     clock
    5.50
    clock
    4.41
    Clock
    3.69
     Clock
    3.61
     clocks
    3.44
    CLOCK
    2.97
     CLOCK
    2.95
     clocked
    2.61
     reloj
    2.42
     Clocks
    2.42
    Activations Density 0.021%

    No Known Activations