© 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. 2274
    Prev
    Next
    INDEX
    Explanations

    feature / column / table

    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
    ﺴ
    1.13
    ｎ
    0.96
    悭
    0.95
    ช่วยเหลือ
    0.88
    ק
    0.88
     Inserting
    0.85
    ResultMessage
    0.85
    ｓ
    0.85
     incendio
    0.84
    ವಾರು
    0.84
    POSITIVE LOGITS
    ism
    0.96
    <td>
    0.90
    ick
    0.86
    ones
    0.85
    ers
    0.83
    isk
    0.82
     but
    0.77
    plasia
    0.77
    ion
    0.75
    igar
    0.75
    Activations Density 0.000%

    No Known Activations