© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 43213
    Prev
    Next
    INDEX
    Explanations

    meth labs, contamination, and datasets

    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
    am
    1.27
     только
    1.27
    ды
    1.20
    uje
    1.19
    ২
    1.18
    。
    1.16
    ir
    1.16
     его
    1.16
    ী
    1.16
    ։
    1.16
    POSITIVE LOGITS
    س
    1.63
    سلم
    1.31
    е
    1.19
    ل
    1.17
     adduced
    1.11
    <0xA2>
    1.10
    <0xA5>
    1.05
    Historically
    1.05
     Şimdi
    1.04
    inafter
    1.03
    Activations Density 0.000%

    No Known Activations