© 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. 57871
    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
     alluminio
    -0.79
    ChangePassword
    -0.75
    一瞬
    -0.73
    的机会
    -0.72
    Cura
    -0.71
    Ako
    -0.70
     playthrough
    -0.69
    չ
    -0.69
    Tahun
    -0.69
     ListView
    -0.69
    POSITIVE LOGITS
     clock
    2.23
     around
    2.06
     round
    1.90
    around
    1.77
    round
    1.73
    clock
    1.71
    Around
    1.70
     Around
    1.55
     Clock
    1.41
    Round
    1.34
    Activations Density 0.017%

    No Known Activations