© 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. 79661
    Prev
    Next
    INDEX
    Explanations

    recipes, lessons, consequences, sealants

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

    United States, safety, music

    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
    glucos
    0.50
    0.46
     mlflow
    0.45
     accedere
    0.45
    v
    0.44
     blight
    0.43
    ̀n
    0.43
    ।
    0.43
     geslacht
    0.43
     uptick
    0.43
    POSITIVE LOGITS
     தானே
    0.49
    Recipe
    0.47
    amiliar
    0.44
     세상
    0.43
     Пен
    0.42
     minutes
    0.42
     PopupWindow
    0.42
    akespeare
    0.41
    ASES
    0.41
    ার্থে
    0.41
    Activations Density 0.001%

    No Known Activations