© 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. 12259
    Prev
    Next
    INDEX
    Explanations

    an internal clock

    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
    ب
    0.86
    </h6>
    0.84
     primeras
    0.77
     Balloon
    0.76
    Б
    0.76
    ‬
    0.75
    </em>
    0.75
     integrantes
    0.74
     incidents
    0.73
     adanya
    0.73
    POSITIVE LOGITS
    勍
    0.96
    यें
    0.94
    ëren
    0.84
    หมือน
    0.80
    schutz
    0.79
    lle
    0.79
    wann
    0.78
    ட்கள்
    0.77
    สต์
    0.77
     verdadeiro
    0.77
    Activations Density 0.001%

    No Known Activations