© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15955
    Prev
    Next
    INDEX
    Explanations

    URLs, code-like tokens, and specific words

    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
     luogo
    0.99
    語
    0.96
    ত্ম
    0.93
     ingresar
    0.89
     entry
    0.87
     felis
    0.87
     poderá
    0.87
     unint
    0.86
     innate
    0.86
    域
    0.84
    POSITIVE LOGITS
    deb
    1.53
    nourished
    1.45
    shoot
    1.39
    𝑔
    1.39
    dDevice
    1.38
    carbons
    1.36
     اداره
    1.33
    Bullets
    1.32
    dioxide
    1.31
    Einzel
    1.31
    Activations Density 0.000%

    No Known Activations