© 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. 41923
    Prev
    Next
    INDEX
    Explanations

    children and future deaths

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

    American Universities, create goods, lending activities

    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
    ྒ
    0.56
     королев
    0.53
     rougeâtre
    0.50
     демокра
    0.49
    ری
    0.47
    ні
    0.47
    intégration
    0.46
    ğinin
    0.46
     آز
    0.46
     замет
    0.46
    POSITIVE LOGITS
    _{\{
    0.44
     estuaries
    0.44
     windows
    0.44
     baits
    0.42
     Medications
    0.42
     Jarvis
    0.42
     scripts
    0.41
     misconception
    0.41
     Mrs
    0.41
    ,&
    0.41
    Activations Density 0.000%

    No Known Activations