© 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. 30744
    Prev
    Next
    INDEX
    Explanations

    kg or kilos

    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
    ৭
    1.48
    е
    1.42
     outperformed
    1.40
    𝚕
    1.37
    𝑺
    1.34
    𝑫
    1.33
     at
    1.32
    д
    1.32
    𝐵
    1.31
    に
    1.30
    POSITIVE LOGITS
    вам
    1.46
     noqa
    1.38
    nými
    1.33
    attiyam
    1.30
     vse
    1.29
    ాలపై
    1.27
    nymi
    1.24
     Į
    1.23
     cárc
    1.23
    stagram
    1.22
    Activations Density 0.000%

    No Known Activations