© 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. 411
    Prev
    Next
    INDEX
    Explanations

    ( formerly known as

    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
     (
    3.81
     ('
    2.48
     (.
    2.47
    (
    2.37
     (-
    2.37
     ("
    2.34
     (~
    2.27
     (‘
    2.23
     (“
    2.22
     (+
    2.19
    POSITIVE LOGITS
    pictured
    2.69
    siehe
    2.67
    excluding
    2.61
    tidak
    2.57
    including
    2.50
    formerly
    2.50
    although
    2.48
    dengan
    2.39
    perhaps
    2.34
    often
    2.30
    Activations Density 0.791%

    No Known Activations