© 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. 3154
    Prev
    Next
    INDEX
    Explanations

    iv/i followed by endings like -ative, -ation, -ada

    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
    м
    1.55
    م
    1.55
    ل
    1.45
    NING
    1.43
    elina
    1.41
    ણી
    1.38
    其他
    1.29
     hostilities
    1.28
    Null
    1.27
     delicacies
    1.27
    POSITIVE LOGITS
    că
    1.24
    dır
    1.23
     trotz
    1.19
    ส์
    1.16
    ภัณฑ์
    1.13
    Plaintiffs
    1.13
    ou
    1.10
    힣
    1.10
    ac
    1.09
    োধী
    1.08
    Activations Density 0.351%

    No Known Activations