© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 454
    Prev
    Next
    INDEX
    Explanations

    `metadata`, `grace`, `Funds`

    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_12_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
    ів
    0.83
    ৯
    0.79
     மற்றும்
    0.78
     அந்
    0.75
     principalColumn
    0.75
     "*************"
    0.74
    ος
    0.73
     alttext
    0.73
     দ্বীপ
    0.73
     و
    0.72
    POSITIVE LOGITS
    m
    1.24
    y
    1.21
    al
    1.17
     Perkin
    1.06
    x
    1.02
    k
    0.98
     Hanks
    0.97
    ak
    0.96
    lina
    0.96
    is
    0.94
    Activations Density 0.000%

    No Known Activations