© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26573
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite

    calculations with units and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    隧
    0.54
    ཊ
    0.51
     услуг
    0.50
    ස්ට
    0.49
    坝
    0.48
    嫔
    0.48
     বসিয়
    0.47
     begrij
    0.47
    鲈
    0.46
    缙
    0.46
    POSITIVE LOGITS
     or
    0.50
     t
    0.46
     if
    0.45
     off
    0.44
     freedom
    0.44
    <0x0D>
    0.43
    </h4>
    0.43
     Its
    0.43
     mark
    0.42
     MARK
    0.42
    Activations Density 0.023%

    No Known Activations