© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2236
    Prev
    Next
    INDEX
    Explanations

    concept followed by explanation

    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_17_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
    Accordingly
    1.14
    Ainsi
    1.12
    Moreover
    1.02
    Thus
    1.00
    䢍
    0.99
    㕝
    0.99
    According
    0.98
    Consequently
    0.92
    Therefore
    0.91
    喍
    0.91
    POSITIVE LOGITS
     –
    2.57
     -
    2.43
     --
    2.18
     —
    2.05
     ---
    1.88
     −
    1.80
    ……
    1.72
    …..
    1.69
    —
    1.66
     -"
    1.66
    Activations Density 0.324%

    No Known Activations