© 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. 891
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     parachute
    0.90
    achute
    0.82
    unte
    0.82
    parachute
    0.79
    iyaki
    0.79
     improvis
    0.78
     préféré
    0.78
    낑
    0.77
    διά
    0.77
    inosaur
    0.77
    POSITIVE LOGITS
    true
    3.72
    True
    3.67
     true
    3.67
     True
    3.53
     TRUE
    3.47
    TRUE
    3.41
     truth
    3.02
    truth
    2.77
     untrue
    2.77
    False
    2.71
    Activations Density 1.098%

    No Known Activations