© 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. 2356
    Prev
    Next
    INDEX
    Explanations

    noise and change

    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
     formulaire
    1.01
    催
    1.01
    succ
    1.00
     hore
    0.97
     premiership
    0.97
     sauver
    0.96
    MIER
    0.96
     succ
    0.95
     expedited
    0.95
    粤
    0.95
    POSITIVE LOGITS
     noise
    1.88
     inhomogeneities
    1.82
    noise
    1.75
    噪声
    1.74
     inhomogeneity
    1.68
     imperfections
    1.63
    Noise
    1.60
     variability
    1.59
     impurities
    1.58
     Noise
    1.57
    Activations Density 0.535%

    No Known Activations