© 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. 13361
    Prev
    Next
    INDEX
    Explanations

    components and themes

    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
    。
    1.23
    .。
    1.12
    .
    1.12
    ។
    1.11
     pihaknya
    1.07
    windowActionBar
    1.04
    пикир
    1.03
    を得
    1.01
    艶
    1.00
     Dens
    0.98
    POSITIVE LOGITS
    S
    1.64
    I
    1.56
    K
    1.54
    R
    1.52
    V
    1.49
    G
    1.48
    U
    1.48
    M
    1.45
    Y
    1.41
    J
    1.38
    Activations Density 0.479%

    No Known Activations