© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8713
    Prev
    Next
    INDEX
    Explanations

    reinforcement learning

    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
    itty
    0.81
    ocz
    0.80
    hxx
    0.78
    πισ
    0.77
    zeros
    0.76
    a
    0.75
    et
    0.75
    able
    0.74
    uola
    0.74
    øn
    0.74
    POSITIVE LOGITS
     Jaeger
    1.15
     contrat
    1.12
    扈
    1.09
     Pochettino
    1.07
     Pinto
    0.99
     Wenger
    0.98
     Lille
    0.95
     jean
    0.94
     野
    0.94
     apache
    0.93
    Activations Density 0.001%

    No Known Activations