© 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. 10785
    Prev
    Next
    INDEX
    Explanations

    although/although

    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
    ್
    3.43
    𝑎
    3.31
    ו
    3.21
    يارات
    3.08
    า
    3.02
    ে
    2.79
    एं
    2.72
    𝙜
    2.69
    ֆ
    2.67
    eredReader
    2.66
    POSITIVE LOGITS
    اً
    2.97
    dan
    2.93
    dom
    2.87
    uh
    2.52
    closest
    2.51
    gy
    2.49
    taus
    2.47
    واع
    2.46
    lov
    2.39
    kh
    2.32
    Activations Density 0.016%

    No Known Activations