© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13787
    Prev
    Next
    INDEX
    Explanations

    robotic or repetitive responses

    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
    ural
    2.14
    rai
    2.04
    ure
    2.02
    िया
    1.98
    urous
    1.96
    傕
    1.96
    ria
    1.90
    ాలు
    1.89
    रे
    1.88
    क
    1.83
    POSITIVE LOGITS
     bagels
    2.08
     elevate
    1.91
    inheritdoc
    1.88
     atletas
    1.84
     bagel
    1.84
    𝘆
    1.81
     elevada
    1.81
     enl
    1.81
     reckon
    1.80
     dependents
    1.77
    Activations Density 0.014%

    No Known Activations