© 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. 8767
    Prev
    Next
    INDEX
    Explanations

    descriptive qualities

    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
     principales
    1.84
     fleste
    1.71
    o
    1.69
    u
    1.67
     peces
    1.56
    ا
    1.56
     chlorides
    1.53
     centrales
    1.52
     tannins
    1.50
     classiques
    1.48
    POSITIVE LOGITS
    和一个
    1.34
    1.23
    И
    1.23
    DIR
    1.17
     Decree
    1.16
    ifference
    1.15
    ite
    1.13
    agger
    1.12
     होना
    1.10
    ist
    1.09
    Activations Density 1.435%

    No Known Activations