© 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. 5276
    Prev
    Next
    INDEX
    Explanations

    foreign scripts

    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
    ó
    0.28
     a
    0.26
    ਾ
    0.26
    as
    0.23
    ä
    0.22
    ักษณะ
    0.22
     vervolgens
    0.22
     the
    0.21
    overnment
    0.21
     retribution
    0.21
    POSITIVE LOGITS
    מ
    0.29
    เรา
    0.29
    ת
    0.28
    你
    0.26
    我们
    0.25
    하여
    0.25
    มีความ
    0.24
    为了
    0.24
    この
    0.24
    ない
    0.24
    Activations Density 0.004%

    No Known Activations