© 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. 3970
    Prev
    Next
    INDEX
    Explanations

    numeric operators and types

    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
     Justice
    0.44
     Publication
    0.44
     Seminary
    0.43
    .
    0.43
    ]
    0.40
    ↵↵
    0.40
     Excellency
    0.40
    )
    0.40
     Museum
    0.40
     Society
    0.39
    POSITIVE LOGITS
    ([(
    0.50
    (*(
    0.49
    (-(
    0.46
    (((
    0.45
     இதுபோன்ற
    0.45
     подобных
    0.43
     числе
    0.42
    ことで
    0.42
    indices
    0.41
    affichage
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.