© 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-16K
    7. 9697
    Prev
    Next
    INDEX
    Explanations

    questions about API integration or specific products

    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_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
     dishonest
    1.90
    <unused149>
    1.89
     restorative
    1.87
     humiliated
    1.85
    
    1.84
    <unused979>
    1.83
     wrongdoing
    1.80
    <unused1020>
    1.80
     negligent
    1.79
    <unused1061>
    1.78
    POSITIVE LOGITS
    ot
    1.40
    ric
    1.32
    োজ
    1.27
    Profil
    1.20
    साइट
    1.19
    otro
    1.15
     Seg
    1.15
    r
    1.14
    uari
    1.13
    ost
    1.13
    Activations Density 0.000%

    No Known Activations