© 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. 208865
    Prev
    Next
    INDEX
    Explanations

    actions, states, or concepts

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

    sensitive data

    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
    说
    0.46
    0.44
    人
    0.44
    泡沫
    0.43
    都
    0.42
    在庫
    0.41
    言い
    0.40
    gie
    0.40
    無
    0.40
    已
    0.39
    POSITIVE LOGITS
     nuov
    0.54
     bundled
    0.52
    Introduceti
    0.52
     prossima
    0.52
    COMANDA
    0.50
    affiche
    0.49
     क्रमांक
    0.49
     tornare
    0.49
     ನಿಮ್ಮ
    0.48
     அனைவரும்
    0.48
    Activations Density 0.001%

    No Known Activations