© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10621
    Prev
    Next
    INDEX
    Explanations

    Okay, let's break down

    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_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
    зир
    1.12
    缺少
    1.03
    ᓴ
    1.02
    拴
    1.00
     smother
    1.00
     꺼
    1.00
     spearheaded
    1.00
    рур
    0.99
    HEL
    0.98
    ᚋ
    0.98
    POSITIVE LOGITS
     unavoidable
    1.16
     inev
    0.95
     occurrence
    0.89
     inevitable
    0.85
     এটাই
    0.83
     inescapable
    0.82
     Announcements
    0.82
     ঘটবে
    0.79
    Acknowledgement
    0.78
     acqu
    0.78
    Activations Density 0.238%

    No Known Activations