© 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. 1778
    Prev
    Next
    INDEX
    Explanations

    bear plus prepositions/articles

    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
    데
    2.17
    岧
    1.98
    are
    1.94
    ことにより
    1.89
    dır
    1.80
    데요
    1.73
    ायला
    1.70
    های
    1.70
    こと
    1.67
     introns
    1.65
    POSITIVE LOGITS
    ン
    2.47
     brunt
    2.39
    ußen
    2.31
    beitung
    2.13
     propriété
    2.05
    ድግዳ
    2.05
    sière
    2.00
    數據
    1.98
     никак
    1.94
    인
    1.94
    Activations Density 0.004%

    No Known Activations