© 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. 2061
    Prev
    Next
    INDEX
    Explanations

    filtering, joining, or list operations

    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
    {'
    0.97
     پە
    0.92
     해외
    0.88
    ":{"
    0.85
     Parameters
    0.84
    Parameters
    0.84
     {'
    0.83
     {
    0.82
     bureaux
    0.81
     Baca
    0.81
    POSITIVE LOGITS
     leader
    1.18
    ∪
    1.18
     join
    1.15
     member
    1.13
    bigcup
    1.11
     LinkedList
    1.10
     Leader
    1.10
     تجمع
    1.10
    iterator
    1.08
     integrante
    1.07
    Activations Density 0.039%

    No Known Activations