© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 13755
    Prev
    Next
    INDEX
    Explanations

    say "operator"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    False
    0.67
     )(
    0.65
    弟弟
    0.64
    })(
    0.64
    bool
    0.64
    startswith
    0.64
    FALSE
    0.61
    ((-
    0.60
    THANK
    0.60
    [](
    0.59
    POSITIVE LOGITS
     null
    1.53
    null
    1.31
     !=
    1.15
    !=
    1.04
     NULL
    1.01
     não
    0.97
    NULL
    0.95
     nullptr
    0.94
    ]!=
    0.92
     Null
    0.91
    Activations Density 0.004%

    No Known Activations