© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4570
    Prev
    Next
    INDEX
    Explanations

    python class

    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
    其
    2.39
    ли
    1.87
    ják
    1.86
    hin
    1.78
    hl
    1.76
    hos
    1.67
    ਆ
    1.67
    ง
    1.66
    hö
    1.65
    hai
    1.64
    POSITIVE LOGITS
    s
    2.36
    ן
    2.27
    ان
    2.13
    ین
    2.09
    rooms
    2.09
    ר
    1.98
    на
    1.84
    parency
    1.80
    ের
    1.77
    liness
    1.73
    Activations Density 0.046%

    No Known Activations