© 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. 14262
    Prev
    Next
    INDEX
    Explanations

    error!

    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
     ‘
    1.58
     thankfully
    1.55
     luckily
    1.54
     subst
    1.47
     prag
    1.44
     самое
    1.43
     fortunately
    1.39
     paragraph
    1.39
     '&
    1.38
     ●
    1.37
    POSITIVE LOGITS
    storeItem
    1.75
     indígenas
    1.74
     outils
    1.74
    på
    1.70
    pleri
    1.67
     społec
    1.67
    Indoor
    1.67
    ुकी
    1.66
    照顾
    1.65
     afuera
    1.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.