© 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. 31713
    Prev
    Next
    INDEX
    Explanations

    success/succeeding

    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
    ни
    1.64
    ש
    1.59
    ي
    1.58
    с
    1.44
    й
    1.40
    י
    1.38
    č
    1.34
    एसआय
    1.33
    ি
    1.32
    एस
    1.31
    POSITIVE LOGITS
    iq
    1.35
    iw
    1.31
    ERAL
    1.26
    iin
    1.23
    وها
    1.23
     soundness
    1.22
    iye
    1.21
     runde
    1.20
    ческие
    1.19
    k
    1.18
    Activations Density 0.001%

    No Known Activations