© 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. 13-GEMMASCOPE-2-RES-16K
    7. 3763
    Prev
    Next
    INDEX
    Explanations

    AI disclaimers about professional advice

    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_13_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
    𝘴
    2.22
    𝘦
    2.06
    ग्विजय
    2.02
    𝘭
    2.01
    𝘥
    1.95
     defaultstate
    1.93
    𝘳
    1.88
    ́
    1.83
     pensa
    1.81
    𝐬
    1.80
    POSITIVE LOGITS
    os
    1.98
    adder
    1.93
    يّ
    1.85
    ängel
    1.84
    ية
    1.84
    ingar
    1.84
    ❤️❤️
    1.83
    يًا
    1.82
    aranth
    1.79
    imis
    1.76
    Activations Density 0.077%

    No Known Activations