© 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. 8842
    Prev
    Next
    INDEX
    Explanations

    explaining things as complex

    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
     multifaceted
    1.52
     truly
    1.45
     wondrous
    1.38
     prelude
    1.38
     byproduct
    1.36
     tremendous
    1.36
    <unused2130>
    1.35
    <unused2125>
    1.34
     hugely
    1.34
     inherently
    1.33
    POSITIVE LOGITS
     and
    1.64
     restantes
    1.58
     и
    1.53
     It
    1.50
     và
    1.45
    It
    1.44
    และ
    1.42
     it
    1.41
     This
    1.38
     которые
    1.38
    Activations Density 0.130%

    No Known Activations