© 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. 2505
    Prev
    Next
    INDEX
    Explanations

    day

    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
    che
    1.75
    ⣀
    1.71
     st
    1.56
    Che
    1.56
    ché
    1.56
     імені
    1.55
    桿
    1.52
    묶
    1.52
     rende
    1.50
    는
    1.46
    POSITIVE LOGITS
    OfWeek
    2.70
     Afternoon
    2.48
    ्ञ
    2.43
     afternoons
    2.30
     afternoon
    2.30
    \">
    2.07
    ചര്യ
    2.06
     pomeriggio
    2.04
     viernes
    1.99
     araw
    1.98
    Activations Density 0.464%

    No Known Activations