© 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. 10852
    Prev
    Next
    INDEX
    Explanations

    ways to express actions

    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
    끔
    1.13
     consideración
    0.95
     چیز
    0.94
    ことなく
    0.93
    粆
    0.91
    ല്‍
    0.91
    ｍｍ
    0.90
    andfeel
    0.90
     점점
    0.90
    彗
    0.90
    POSITIVE LOGITS
    ’
    0.90
    )—
    0.77
     via
    0.75
    '
    0.75
    apolis
    0.75
    —
    0.74
    ise
    0.74
     ran
    0.72
    ize
    0.71
    naire
    0.71
    Activations Density 0.304%

    No Known Activations