© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3769
    Prev
    Next
    INDEX
    Explanations

    'll.ë.ch.sch.ulle

    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
    sul
    1.44
    ung
    1.38
    ні
    1.34
    𝗮
    1.31
     appellant
    1.30
     строку
    1.23
     путь
    1.22
    𝘢
    1.20
    orderInCategory
    1.18
    LabelTool
    1.17
    POSITIVE LOGITS
    ,
    2.09
    y
    1.52
    u
    1.38
    ব
    1.36
    et
    1.33
    ka
    1.33
    ۥ
    1.28
    ა
    1.27
    ET
    1.21
    EM
    1.21
    Activations Density 0.000%

    No Known Activations