© 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. 99
    Prev
    Next
    INDEX
    Explanations

    release power, Balance Sheet, ordinary shares, passing laws, Approval of Minutes, primary cluster, impacted industries

    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
    ()=>{
    1.61
    theless
    1.60
     😂😂
    1.59
     DOJ
    1.55
    ปลอดภัย
    1.53
    第壹百
    1.52
     downlink
    1.51
     Kubrick
    1.49
    াযোগ
    1.47
     Außerdem
    1.47
    POSITIVE LOGITS
    нические
    1.55
    ının
    1.50
     fixe
    1.45
    ين
    1.42
    ğı
    1.38
    с
    1.36
     Nası
    1.35
    IS
    1.34
    emois
    1.31
    ﺪ
    1.30
    Activations Density 0.000%

    No Known Activations