© 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. 798
    Prev
    Next
    INDEX
    Explanations

    environmental regulations, free shipping, various sources, chess notation, code snippets

    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
    ukiyoe
    1.35
    Accounts
    1.29
    trav
    1.27
    grafo
    1.26
    ḳ
    1.25
    owanym
    1.25
    Kaynakça
    1.24
     kerana
    1.23
    Hor
    1.23
    ቈ
    1.22
    POSITIVE LOGITS
     steps
    1.10
     actions
    1.07
     конкре
    1.00
    نر
    0.97
     outcomes
    0.96
    levance
    0.95
     posture
    0.93
     follow
    0.92
     betterment
    0.90
     outreach
    0.90
    Activations Density 0.000%

    No Known Activations