© 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. 74493
    Prev
    Next
    INDEX
    Explanations

    dates and facts

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

    liver damage alcohol

    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
     ৪
    0.47
    ünün
    0.46
     receivables
    0.46
     PAYMENT
    0.46
    ់
    0.45
    ꯡ
    0.45
     πρώ
    0.45
     reco
    0.44
     noches
    0.44
     gründ
    0.44
    POSITIVE LOGITS
     Temperaturen
    0.48
     Langkah
    0.44
     Nurs
    0.42
     Kyoto
    0.42
    烜
    0.42
     सितंबर
    0.41
     Vorg
    0.41
     September
    0.40
     இடத்தை
    0.40
     Erik
    0.40
    Activations Density 0.001%

    No Known Activations