© 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. 12759
    Prev
    Next
    INDEX
    Explanations

    index of target

    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
     উইল
    1.42
     barbell
    1.33
    bells
    1.31
     individuos
    1.28
     sensors
    1.25
     phenyl
    1.25
     类型
    1.25
    ﺑ
    1.25
    𝔹
    1.24
     功能
    1.24
    POSITIVE LOGITS
     Sustainable
    1.10
    Sustainable
    1.04
     for
    0.94
     sustainable
    0.93
     Highlands
    0.93
    <0x8B>
    0.92
    ↵
    0.88
     Photo
    0.85
    죄
    0.85
     Peace
    0.84
    Activations Density 0.006%

    No Known Activations