© 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. 3465
    Prev
    Next
    INDEX
    Explanations

    important notes

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of numeric tokens or number-like figures (quantities, measurements, digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     \%$.
    0.79
     Hälfte
    0.79
     bepa
    0.73
    만이
    0.71
    and
    0.70
    The
    0.70
     coisa
    0.70
    だけ
    0.67
     Not
    0.67
     \%$,
    0.67
    POSITIVE LOGITS
     दिवसीय
    0.80
    霟
    0.77
     सदस्यीय
    0.75
    idential
    0.74
    opharmaceutical
    0.72
    યર
    0.70
     audiovisual
    0.69
     transatlantic
    0.69
     multilevel
    0.68
     multifaceted
    0.68
    Activations Density 0.283%

    No Known Activations