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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 998
    Prev
    Next
    INDEX
    Explanations

    animals and nature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     с
    1.45
     в
    1.42
     في
    1.28
     В
    1.26
     من
    1.24
     ر
    1.22
     بت
    1.18
     О
    1.17
     С
    1.15
     Ка
    1.14
    POSITIVE LOGITS
     alcoholism
    1.29
    ständig
    1.27
     alkohol
    1.25
    <unused386>
    1.22
    이렇게
    1.17
     cír
    1.17
    kast
    1.16
     Veränderungen
    1.15
    हालांकि
    1.15
     alanine
    1.14
    Activations Density 0.001%

    No Known Activations