© 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. 11141
    Prev
    Next
    INDEX
    Explanations

    database names, mysql, redis

    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
    urile
    1.64
    vous
    1.49
    o
    1.49
    el
    1.47
    as
    1.41
    ur
    1.38
    újt
    1.36
    urpose
    1.33
    efficacité
    1.33
     וח
    1.33
    POSITIVE LOGITS
    да
    1.57
    Ⲙ
    1.34
    สัน
    1.28
    納得
    1.28
    ن
    1.27
     проблема
    1.26
    CameraOpened
    1.25
     строк
    1.24
    ла
    1.22
    λλ
    1.22
    Activations Density 0.043%

    No Known Activations