© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    apple products and fruits

    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
    ява
    0.81
    тік
    0.77
    侃
    0.76
     Own
    0.76
     Yes
    0.75
     propia
    0.75
    ová
    0.74
    šć
    0.74
    aha
    0.74
    ipun
    0.73
    POSITIVE LOGITS
     liaison
    1.21
     ambitions
    1.13
     remit
    1.08
    🧔
    1.06
     motives
    1.06
     residences
    1.02
     deliverables
    1.02
     REGULATIONS
    1.01
     JOSE
    1.00
    🆔
    1.00
    Activations Density 0.088%

    No Known Activations