© 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. 603
    Prev
    Next
    INDEX
    Explanations

    rounding to nearest ten

    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
     lunga
    1.58
     rifiuti
    1.56
     élő
    1.56
     alimentare
    1.54
    atiche
    1.52
     ragazza
    1.45
     "/"
    1.42
     Б
    1.38
     vett
    1.36
    ДС
    1.36
    POSITIVE LOGITS
    kne
    1.65
    ória
    1.58
     repaired
    1.50
     repair
    1.49
    repair
    1.48
     orthopedic
    1.47
    Repair
    1.46
     Orphans
    1.45
    orie
    1.45
     replaced
    1.44
    Activations Density 0.000%

    No Known Activations