© 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-262K
    7. 4908
    Prev
    Next
    INDEX
    Explanations

    multi-lingual punctuation and bold markers

    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_262k_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
     superfici
    1.31
    은
    1.24
    २
    1.20
    १
    1.19
    "
    1.09
    .
    1.08
    京
    1.07
    반
    1.06
    %%%%%%%%%%%%%%%%
    1.05
     strollers
    1.05
    POSITIVE LOGITS
    و
    2.02
    س
    1.82
    zelfde
    1.81
    ا
    1.76
    dır
    1.63
    ין
    1.62
    ق
    1.61
    et
    1.60
    ه
    1.57
    هي
    1.48
    Activations Density 2.837%

    No Known Activations