© 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-65K
    7. 577
    Prev
    Next
    INDEX
    Explanations

    perhaps maybe options

    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_65k_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
    .
    1.08
    ,
    1.03
     .
    0.92
     .(
    0.90
     的
    0.89
    .[
    0.85
     (
    0.84
    :
    0.84
    .(
    0.77
     (.
    0.76
    POSITIVE LOGITS
    если
    1.18
    というか
    1.15
    maybe
    1.07
    unlike
    1.06
    since
    1.05
    hopefully
    1.05
    although
    1.04
    depending
    1.03
    assuming
    1.03
    ্ভব
    1.02
    Activations Density 0.333%

    No Known Activations