© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 7630
    Prev
    Next
    INDEX
    Explanations

    polygon, timeline, median, parabola

    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
     devastating
    1.79
    י
    1.73
    𝙚
    1.69
    հ
    1.67
    将
    1.66
     fanfare
    1.61
     asparagus
    1.55
    ો
    1.54
    𝚟
    1.54
    ской
    1.53
    POSITIVE LOGITS
    i
    2.47
    aquest
    2.16
    eritud
    2.11
    el
    2.08
    er
    1.95
    es
    1.92
    orable
    1.91
    त
    1.91
    ி
    1.88
    ality
    1.85
    Activations Density 0.143%

    No Known Activations