© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15047
    Prev
    Next
    INDEX
    Explanations

    SCP documentation

    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
     könnte
    0.84
     Мы
    0.84
     könnten
    0.83
     môže
    0.83
    ꩡ
    0.83
     kostet
    0.83
     sollte
    0.82
    ционный
    0.82
     Bộ
    0.82
     kiezen
    0.81
    POSITIVE LOGITS
    не
    0.80
    cur
    0.78
     சேர்த்து
    0.77
    ✔️
    0.77
    stacks
    0.75
     itself
    0.74
    рабо
    0.73
    鳖
    0.73
    ים
    0.72
    stances
    0.72
    Activations Density 0.000%

    No Known Activations