© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    names of software and models

    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
     BSData
    1.78
     MQTT
    1.58
     HUOBI
    1.56
    宩
    1.55
     quadrada
    1.52
     análise
    1.51
     Appodeal
    1.51
     IUnary
    1.51
     verificación
    1.51
     interação
    1.51
    POSITIVE LOGITS
     "
    0.88
     “
    0.87
    0.84
     nation
    0.81
     ‘
    0.80
     '
    0.79
     Nation
    0.78
    ’
    0.75
    '
    0.75
     capital
    0.72
    Activations Density 3.221%

    No Known Activations