© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 42436
    Prev
    Next
    INDEX
    Explanations

    inspection and related words

    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
    Μ
    1.25
    $\\
    1.24
     popupButton
    1.15
    Cheers
    1.12
    dataset
    1.10
     médical
    1.10
    d
    1.09
    𝟏
    1.09
    IES
    1.08
     Cheers
    1.08
    POSITIVE LOGITS
    zelfde
    1.58
    ‌هایی
    1.48
    ‌ای
    1.43
    तून
    1.41
    و
    1.41
    न
    1.37
    ar
    1.31
    йд
    1.30
    ah
    1.29
    ീഷ
    1.27
    Activations Density 0.002%

    No Known Activations