© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1191
    Prev
    Next
    INDEX
    Explanations

    complex situations and societal issues

    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_24_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
     Solutions
    0.79
     Sasuke
    0.69
     Tribunal
    0.68
     Indices
    0.68
     八
    0.67
     식으로
    0.67
     Su
    0.67
     Transport
    0.66
    4
    0.66
     Relief
    0.64
    POSITIVE LOGITS
    tega
    0.92
    incision
    0.91
    не
    0.88
    soci
    0.88
    quantidade
    0.85
    attiv
    0.85
    τα
    0.84
    utiliser
    0.84
    intero
    0.82
    estructura
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.