© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3192
    Prev
    Next
    INDEX
    Explanations

    introducing explanations or lists

    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
    𝐥
    3.29
    𝐬
    2.69
    ನಲ್ಲಿ
    2.63
    𝐢
    2.61
    اً
    2.51
    𝘭
    2.49
    𝐦
    2.49
    tenance
    2.48
    兀
    2.32
    𝐨
    2.30
    POSITIVE LOGITS
    ות
    3.55
    ي
    3.43
    ্ম্ম
    3.32
    ar
    3.30
    м
    3.27
    ಿ
    3.20
    anik
    2.98
    ותו
    2.97
    й
    2.96
    ו
    2.96
    Activations Density 0.065%

    No Known Activations