© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5672
    Prev
    Next
    INDEX
    Explanations

    it's imported

    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_13_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
    これは
    1.23
    <h2>
    1.07
     Almost
    1.05
     cuánt
    1.04
     Your
    1.00
     это
    1.00
    <h3>
    0.99
    это
    0.99
    </blockquote>
    0.98
    your
    0.98
    POSITIVE LOGITS
    ⨯
    1.24
    $\--
    1.23
    <unused100>
    1.19
    ̕
    1.19
     sword
    1.18
     cathedral
    1.17
    κη
    1.17
     swords
    1.16
    ;"
    1.16
    ;(
    1.15
    Activations Density 0.317%

    No Known Activations