© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9769
    Prev
    Next
    INDEX
    Explanations

    patterns you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     toplam
    0.57
     കള
    0.56
     ue
    0.56
     mathvariant
    0.50
     hapless
    0.49
    getDefaultSh
    0.49
     mostrado
    0.49
    \},
    0.48
     स्क्वायर
    0.48
     세제곱
    0.48
    POSITIVE LOGITS
     VENT
    0.58
    هران
    0.54
     Dodson
    0.53
    負担
    0.52
    VENT
    0.52
     grantees
    0.51
    充电
    0.51
     evenly
    0.50
    DON
    0.50
    جار
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.