© 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. 111194
    Prev
    Next
    INDEX
    Explanations

    back again

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

    chest pain and discomfort

    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
     diver
    0.44
    ة
    0.43
     ebenfalls
    0.43
    Target
    0.41
    MARK
    0.41
    ในการ
    0.40
    に対
    0.40
     acumen
    0.40
     MARK
    0.40
    を設定
    0.40
    POSITIVE LOGITS
    urile
    0.50
    itabbam
    0.49
    dır
    0.49
    ąd
    0.49
    锹
    0.48
     사람은
    0.47
    rui
    0.46
     trueMap
    0.46
     จํานวน
    0.45
    dus
    0.45
    Activations Density 0.002%

    No Known Activations