© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4801
    Prev
    Next
    INDEX
    Explanations

    academic and programming contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ی
    1.09
    a
    1.00
    eep
    0.96
    e
    0.96
    oł
    0.93
    eel
    0.92
    ej
    0.92
    eo
    0.90
     часу
    0.88
    y
    0.87
    POSITIVE LOGITS
     significado
    0.89
    ClFN
    0.87
     представлены
    0.86
    きた
    0.84
    ではなく
    0.84
    様
    0.84
    ार्क
    0.84
     przedstaw
    0.82
     temel
    0.80
     llamadas
    0.80
    Activations Density 0.001%

    No Known Activations