© 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. 200923
    Prev
    Next
    INDEX
    Explanations

    money or transactions

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

    retail, away, data, AS numbers, optimizers, gap

    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
     څ
    0.53
    可以将
    0.49
    vart
    0.48
     将
    0.47
     povas
    0.47
     proviene
    0.46
     glLightfv
    0.45
     entom
    0.45
     रविदास
    0.45
     for
    0.44
    POSITIVE LOGITS
    लक्ष्मी
    0.47
    会話
    0.47
    Phones
    0.44
    ภ
    0.43
    ABLES
    0.43
     Cameras
    0.42
    Books
    0.42
    サイン
    0.42
    िंट
    0.42
     GIFs
    0.41
    Activations Density 0.000%

    No Known Activations