© 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. 2572
    Prev
    Next
    INDEX
    Explanations

    has/have been

    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
    getValue
    2.85
    mL
    2.67
    pmap
    2.63
     ipsum
    2.63
    pload
    2.61
    틴
    2.61
     अफेयर्स
    2.57
    getCamera
    2.55
    ่า
    2.46
    Override
    2.43
    POSITIVE LOGITS
    稞
    3.09
    靂
    2.82
    จํา
    2.80
    ه
    2.69
    νε
    2.66
    craft
    2.66
    𝗿
    2.59
    liess
    2.55
     ».
    2.52
    しい
    2.49
    Activations Density 0.188%

    No Known Activations