© 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. 9444
    Prev
    Next
    INDEX
    Explanations

    append and appendix

    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
     iż
    1.86
    지만
    1.84
    লা
    1.80
    ą
    1.80
    ות
    1.75
    ية
    1.68
    ১৮
    1.66
    ين
    1.63
     conjunction
    1.63
     Mudah
    1.63
    POSITIVE LOGITS
    talk
    2.16
    tod
    2.16
    t
    2.16
    PRI
    2.09
    tio
    2.02
    ா
    1.98
    帙
    1.95
    েও
    1.91
    tweets
    1.84
    cosec
    1.83
    Activations Density 0.047%

    No Known Activations