© 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. 11397
    Prev
    Next
    INDEX
    Explanations

    turbo attention

    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
    𝒊
    2.88
    ে
    2.72
    𝒔
    2.70
    𝒈
    2.63
    𝒐
    2.55
    slope
    2.54
    𝒖
    2.52
    𝒅
    2.51
    amaks
    2.48
    enic
    2.43
    POSITIVE LOGITS
    ತ್ರೆ
    2.48
    ້ມ
    2.36
    empre
    2.31
    षण
    2.29
    com
    2.27
    AnimationFrame
    2.25
    IRQHandler
    2.20
     நிலையம்
    2.18
     ruangan
    2.16
    brig
    2.15
    Activations Density 0.001%

    No Known Activations