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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1102
    Prev
    Next
    INDEX
    Explanations

    ease and difficulty of communication

    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
     அருகில்
    1.22
     谢
    1.21
    ɽ
    1.17
    મ
    1.15
     끝나
    1.15
     ジ
    1.15
     تاہم
    1.14
     예약
    1.13
     ซ
    1.12
     সর
    1.12
    POSITIVE LOGITS
     patrim
    1.12
    内外
    1.11
     stockholder
    1.06
     coffers
    1.05
     finances
    1.03
    Distinct
    1.01
     fidèle
    0.99
     स्वभाव
    0.99
     tangible
    0.99
     patrimoine
    0.97
    Activations Density 0.936%

    No Known Activations