© 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. 34-GEMMASCOPE-RES-131K
    7. 1286
    Prev
    Next
    INDEX
    Explanations

    appears or seems

    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
     presumably
    -0.83
     probably
    -0.79
     Probably
    -0.78
     Prenez
    -0.78
     sesión
    -0.75
     angusti
    -0.75
    进攻
    -0.72
     obviously
    -0.71
     pantalla
    -0.70
    ึกษา
    -0.69
    POSITIVE LOGITS
     appears
    2.19
     appeared
    2.11
     appear
    2.09
     seem
    1.87
     Appears
    1.77
     seems
    1.77
     Appear
    1.77
     seemed
    1.76
     appearing
    1.72
    appear
    1.66
    Activations Density 0.068%

    No Known Activations