© 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. 2369
    Prev
    Next
    INDEX
    Explanations

    origins, what it is

    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
    1.22
    0
    0.96
    3
    0.96
    1
    0.93
    2
    0.93
    p
    0.91
    n
    0.89
    ed
    0.88
    B
    0.88
    5
    0.87
    POSITIVE LOGITS
     спорт
    0.97
    💠
    0.97
     systèmes
    0.89
     mécanismes
    0.89
     véritables
    0.84
    Mâc
    0.83
     spaceleft
    0.82
    логия
    0.82
     quatrième
    0.81
     ambito
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.