Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 15416
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    кана
    1.27
     insanely
    1.21
    非常
    1.21
    ¥
    1.14
    isure
    1.13
    ہ
    1.13
    <unused1856>
    1.09
     relentlessly
    1.08
    俶
    1.08
    ையின்
    1.05
    POSITIVE LOGITS
     דער
    1.17
     paz
    1.10
    េច
    1.05
     pronounce
    1.01
     Между
    0.98
     Dar
    0.96
    ومین
    0.96
    김포
    0.93
    ៊ី
    0.92
    slüman
    0.92
    Activations Density 0.010%

    No Known Activations