© 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. 7-GEMMASCOPE-2-RES-16K
    7. 124
    Prev
    Next
    INDEX
    Explanations

    let's + action verb

    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_7_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
    sw
    1.17
     (
    1.15
    selves
    1.14
    would
    1.12
     selves
    1.10
    sling
    1.09
    t
    1.06
     would
    1.05
     degrading
    1.05
    could
    1.04
    POSITIVE LOGITS
     badań
    2.72
     inoltre
    2.49
     âmbito
    2.44
    okatokat
    2.41
    <unused1568>
    2.34
     choisissez
    2.34
     incrível
    2.33
     istraž
    2.32
     tampilan
    2.31
     également
    2.31
    Activations Density 9.572%

    No Known Activations