© 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. 11965
    Prev
    Next
    INDEX
    Explanations

    PT followed by acronyms or abbreviations

    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
    িসি
    3.32
    ﾞ
    3.23
    Leod
    2.75
    ங்கிணை
    2.71
    ᴰ
    2.65
    ِّف
    2.65
     finement
    2.64
    ulates
    2.60
     täht
    2.56
    ément
    2.55
    POSITIVE LOGITS
    ت
    3.29
    tr
    2.86
    henius
    2.86
    tat
    2.81
    कमा
    2.65
    tas
    2.51
    퍽
    2.49
    onz
    2.48
    tric
    2.48
    ी
    2.45
    Activations Density 0.004%

    No Known Activations