© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 13484
    Prev
    Next
    INDEX
    Explanations

    summarize or overview

    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
    癀
    1.76
    ました
    1.71
    toned
    1.70
    nej
    1.69
    scription
    1.66
    ning
    1.63
    kus
    1.60
    larım
    1.58
    distortion
    1.57
    matik
    1.56
    POSITIVE LOGITS
    ة
    1.90
    us
    1.80
    ּ
    1.66
    ת
    1.65
    ing
    1.62
    า
    1.55
    स
    1.40
    ї
    1.36
    BERS
    1.34
    كيف
    1.34
    Activations Density 0.055%

    No Known Activations