© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1748
    Prev
    Next
    INDEX
    Explanations

    reusable, repeatable, reproducible

    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_17_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
     "
    1.03
     “
    0.99
     «
    0.85
     „
    0.83
     India
    0.83
     Bangalore
    0.83
     Indien
    0.74
    「
    0.74
     Hyderabad
    0.74
    ("
    0.73
    POSITIVE LOGITS
     pathlib
    1.22
    AnimationClip
    1.15
     tqdm
    1.14
     IPython
    1.13
     chalc
    1.07
    ignty
    1.04
     PyQt
    1.04
    <unused1009>
    1.04
     الاعداد
    1.03
    qdm
    1.02
    Activations Density 0.013%

    No Known Activations