© 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. 12771
    Prev
    Next
    INDEX
    Explanations

    Llama, Vicuna models

    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
    臾
    2.11
     lar
    2.10
     грн
    2.03
    ਊ
    2.00
    Ϻ
    1.96
     ler
    1.89
     m
    1.84
    ends
    1.83
    𝗯
    1.81
    很
    1.81
    POSITIVE LOGITS
    tanto
    3.20
    e
    3.17
    ea
    2.93
    ことなく
    2.90
    t
    2.85
    ا
    2.83
    i
    2.74
    ي
    2.72
    นี่
    2.67
    iin
    2.62
    Activations Density 0.179%

    No Known Activations