© 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. 13744
    Prev
    Next
    INDEX
    Explanations

    EPA and NIST resources

    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
    اا
    2.94
     corriendo
    2.83
    dzić
    2.83
    quela
    2.79
    اگ
    2.79
    dDevice
    2.75
    erà
    2.70
    ו
    2.70
    दर्द
    2.69
    וה
    2.69
    POSITIVE LOGITS
     co
    2.22
     lysate
    2.14
     ellips
    1.88
    adians
    1.85
     class
    1.84
     walls
    1.84
     membranes
    1.83
     game
    1.81
     ref
    1.78
     membrane
    1.75
    Activations Density 0.069%

    No Known Activations