© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2163
    Prev
    Next
    INDEX
    Explanations

    enter, exit, clearing, nerve, disturbing

    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
     ‘
    2.48
    ’.”
    2.39
    ’,
    2.26
    𝑐
    2.21
    
    2.18
    𝑟
    2.14
    ing
    2.13
    spiration
    2.12
    xty
    2.12
    𝑤
    2.11
    POSITIVE LOGITS
    ígono
    3.07
    "，
    2.94
    "。
    2.87
    িতে
    2.84
    mités
    2.77
     résult
    2.76
    冈
    2.70
    iviato
    2.69
    WithType
    2.66
     nere
    2.66
    Activations Density 0.438%

    No Known Activations