© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 809
    Prev
    Next
    INDEX
    Explanations

    limitations or weaknesses

    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
    iseur
    0.97
    亰
    0.96
    ütz
    0.94
    luž
    0.94
    ubat
    0.91
    ước
    0.90
     wyróż
    0.89
     ৭
    0.88
     важней
    0.87
     ಅನ್ನು
    0.86
    POSITIVE LOGITS
     lack
    1.79
     unavailability
    1.79
     reluctance
    1.76
     incompatibility
    1.59
     unwillingness
    1.57
     nervousness
    1.55
     inability
    1.53
     inconsistency
    1.53
    Lack
    1.51
     laziness
    1.50
    Activations Density 1.970%

    No Known Activations