© 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. 10670
    Prev
    Next
    INDEX
    Explanations

    high performance superlatives

    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
     자체가
    1.22
    blow
    1.21
    fade
    1.16
    ).
    1.16
    .)
    1.14
    ామ
    1.12
    )
    1.11
     parable
    1.11
    謐
    1.10
    bleed
    1.10
    POSITIVE LOGITS
    ési
    1.15
    ne
    1.14
    σία
    1.11
    dev
    1.10
    设计
    1.10
    请输入
    1.07
    nt
    1.06
    াদেশ
    1.06
    平均
    1.05
     encarg
    1.05
    Activations Density 0.074%

    No Known Activations