© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2654
    Prev
    Next
    INDEX
    Explanations

    asking questions and exploring possibilities

    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_13_width_65k_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
    ולי
    1.52
    Чита
    1.50
     Refinery
    1.50
    WARDS
    1.49
    Gallery
    1.43
     CONFERENCE
    1.40
     Particle
    1.40
    Ր
    1.39
     ゼ
    1.39
     그림
    1.36
    POSITIVE LOGITS
     spont
    1.08
     tats
    0.98
     actives
    0.98
    ↵
    0.96
     riches
    0.96
     activ
    0.94
    s
    0.94
    diverse
    0.93
     prosper
    0.92
     vars
    0.92
    Activations Density 0.000%

    No Known Activations