© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13740
    Prev
    Next
    INDEX
    Explanations

    what's been happening or on your mind

    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
    aczego
    2.58
    vaart
    2.50
    perceptron
    2.32
    openjdk
    2.32
    𝐇
    2.28
    NSNumber
    2.25
    UNUSED
    2.24
    hams
    2.22
    ret
    2.21
    rische
    2.21
    POSITIVE LOGITS
    どうしても
    2.40
    اا
    2.39
    𝙤
    2.26
    ২২
    2.26
    ことで
    2.24
    ்ப்ப
    2.24
    ا
    2.22
    ্ক
    2.21
    erade
    2.16
    erende
    2.15
    Activations Density 0.031%

    No Known Activations