© 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. 13-GEMMASCOPE-2-RES-16K
    7. 875
    Prev
    Next
    INDEX
    Explanations

    the followed by a descriptor

    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_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
     대표
    1.09
     newly
    1.08
     prestigious
    1.03
     번째
    1.03
     administrative
    1.01
     South
    1.00
     largest
    0.98
     두
    0.98
     National
    0.98
     proposed
    0.97
    POSITIVE LOGITS
     subtlety
    0.85
    things
    0.80
     nigg
    0.77
     durchaus
    0.76
     subtleties
    0.76
    guesses
    0.75
     complacency
    0.74
     вполне
    0.74
    words
    0.74
    chance
    0.74
    Activations Density 1.549%

    No Known Activations