© 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. 14068
    Prev
    Next
    INDEX
    Explanations

    modern animals

    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
     escrita
    1.33
     ăn
    1.25
    ஞ
    1.23
     cum
    1.22
    '>
    1.19
    â
    1.18
     publicada
    1.18
     unlink
    1.17
    ือน
    1.17
    পত্রের
    1.16
    POSITIVE LOGITS
    borderRadius
    1.58
     anderer
    1.57
     Putri
    1.56
     Chargers
    1.53
    كور
    1.52
    𝐇
    1.50
    ophenyl
    1.48
    utzer
    1.47
    emort
    1.46
    笘
    1.46
    Activations Density 0.000%

    No Known Activations