© 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. 8872
    Prev
    Next
    INDEX
    Explanations

    duration of quantity

    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
    ﺎ
    1.56
     dotyczą
    1.48
    ྜ
    1.45
    是他
    1.42
    larından
    1.41
    νες
    1.41
     мира
    1.39
    ਾ
    1.37
     forerunner
    1.35
    ప్పటికీ
    1.34
    POSITIVE LOGITS
    fi
    1.76
    og
    1.70
    ா
    1.68
    h
    1.63
    و
    1.59
    fact
    1.55
    för
    1.55
    ي
    1.53
     الل
    1.52
    t
    1.52
    Activations Density 0.092%

    No Known Activations