© 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. 30528
    Prev
    Next
    INDEX
    Explanations

    compelled to

    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
    ه
    2.59
    ு
    2.19
    اب
    2.16
    甶
    2.05
    هل
    1.99
    ر
    1.98
    ل
    1.93
    ار
    1.91
    e
    1.91
    ে
    1.89
    POSITIVE LOGITS
    른
    1.81
    li
    1.79
    ce
    1.64
     eléct
    1.61
     appels
    1.61
     ư
    1.61
    ж
    1.60
    nél
    1.56
     Einen
    1.56
    Đây
    1.55
    Activations Density 0.010%

    No Known Activations