© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12710
    Prev
    Next
    INDEX
    Explanations

    error handling and messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Presumably
    1.20
     Riemannian
    0.95
     А
    0.94
    Apparently
    0.92
    既然
    0.85
     Б
    0.84
     Apparently
    0.84
     तस्करी
    0.82
     monolayer
    0.82
     अनुसरण
    0.82
    POSITIVE LOGITS
    ै
    0.87
     even
    0.87
    까지
    0.87
     bahkan
    0.79
     never
    0.78
     build
    0.76
     rates
    0.75
    매
    0.75
     pull
    0.74
     charts
    0.73
    Activations Density 0.086%

    No Known Activations