© 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. 2378
    Prev
    Next
    INDEX
    Explanations

    introducing an alternative

    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
    लम
    0.88
     youngest
    0.82
     imaginable
    0.76
    Including
    0.76
    Latest
    0.73
     dames
    0.73
    なか
    0.71
    한
    0.71
     आंच
    0.71
     franch
    0.71
    POSITIVE LOGITS
     instead
    4.88
    Instead
    4.52
    instead
    4.51
     Instead
    4.48
     rather
    3.62
     Rather
    3.57
    Rather
    3.48
     вместо
    3.40
    rather
    3.40
    而是
    3.17
    Activations Density 1.119%

    No Known Activations