© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7890
    Prev
    Next
    INDEX
    Explanations

    assigning or defining variables

    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_16k_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
    ৭
    1.75
    ל
    1.54
    ﻟ
    1.50
    ה
    1.48
    ৩
    1.48
    った
    1.40
    ﺪ
    1.38
    した
    1.38
    ৮
    1.36
    ᴛ
    1.35
    POSITIVE LOGITS
    ak
    1.27
    lara
    1.23
    ný
    1.17
    scapes
    1.16
    ain
    1.13
    larına
    1.13
    ay
    1.13
    services
    1.13
    ness
    1.09
    speople
    1.09
    Activations Density 0.122%

    No Known Activations