© 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. 10634
    Prev
    Next
    INDEX
    Explanations

    comfort and comfortability

    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
    uiar
    2.59
    метка
    2.59
    氀
    2.58
    על
    2.54
    ων
    2.52
    Cuánto
    2.50
    Vai
    2.46
    productivity
    2.46
    ாளர்க
    2.45
    gameObjects
    2.45
    POSITIVE LOGITS
    ্টর
    2.65
    s
    2.25
    ிய
    2.19
    sv
    2.10
    tn
    2.10
    sion
    2.06
    sy
    2.03
    ppen
    2.01
    pert
    1.99
    بات
    1.99
    Activations Density 0.022%

    No Known Activations