© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10563
    Prev
    Next
    INDEX
    Explanations

    `#include <iostream>`

    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_22_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
    quint
    1.07
    atemala
    1.02
    zeta
    1.01
     ranch
    1.00
     Ranch
    0.98
    ֮
    0.97
    agen
    0.97
    inosaur
    0.95
    jones
    0.94
    zag
    0.93
    POSITIVE LOGITS
     Providing
    1.03
     ocor
    1.01
     Plea
    0.91
     Using
    0.88
     Removing
    0.88
     Substit
    0.87
     podendo
    0.87
    >",
    0.86
     Leistung
    0.86
     anún
    0.86
    Activations Density 0.008%

    No Known Activations