© 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. 45123
    Prev
    Next
    INDEX
    Explanations

    local organizations

    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
    ت
    1.63
    ل
    1.42
    па
    1.35
    ש
    1.35
    š
    1.30
    ال
    1.26
     don
    1.26
     we
    1.21
    гө
    1.20
    만
    1.20
    POSITIVE LOGITS
    pra
    1.47
    ную
    1.40
    ería
    1.38
    cą
    1.32
    gramModel
    1.32
    bos
    1.28
     dems
    1.27
    dgs
    1.27
    எஸ்
    1.26
    tej
    1.24
    Activations Density 0.001%

    No Known Activations