© 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. 16245
    Prev
    Next
    INDEX
    Explanations

    informing decisions

    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
    ار
    1.98
    ون
    1.88
    ੀ
    1.79
    ال
    1.77
    ре
    1.76
    ುಕ
    1.74
    ふ
    1.70
    タ
    1.66
    ل
    1.65
    ब
    1.63
    POSITIVE LOGITS
    적인
    1.76
     اگه
    1.75
    ppure
    1.59
    нием
    1.55
    처럼
    1.54
     lakh
    1.53
    是一个
    1.48
     Kona
    1.48
    phones
    1.46
    quila
    1.46
    Activations Density 0.085%

    No Known Activations