© 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. 12822
    Prev
    Next
    INDEX
    Explanations

    compost and yarn claims

    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
     })(
    3.20
     teaspoons
    3.09
    送信
    2.99
    OrCreate
    2.91
    <unused189>
    2.89
     mocks
    2.87
    <unused996>
    2.87
    LLA
    2.87
    OBER
    2.86
     Palabra
    2.85
    POSITIVE LOGITS
    tim
    2.34
    으로써
    2.34
    u
    2.28
    se
    2.27
    en
    2.25
    n
    2.22
    ഡിയോ
    2.21
    정을
    2.16
    蔔
    2.12
    slope
    2.12
    Activations Density 0.007%

    No Known Activations