© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12149
    Prev
    Next
    INDEX
    Explanations

    AR/VR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    used
    2.80
    ото
    2.57
    মন্ত্রীর
    2.38
    ណ្ឌ
    2.30
    ំព
    2.26
    渫
    2.22
    뜸
    2.22
    invasive
    2.20
    ***************
    2.19
    വന്‍
    2.19
    POSITIVE LOGITS
    ्स
    3.50
    了
    2.98
    swear
    2.93
     карте
    2.88
    ্সের
    2.88
    nya
    2.71
    iewicz
    2.69
     Leverage
    2.67
    нюю
    2.62
    ेक्षित
    2.56
    Activations Density 0.003%

    No Known Activations