© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14288
    Prev
    Next
    INDEX
    Explanations

    even / eventually / Edward's notation

    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_7_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
    ly
    2.55
    으로써
    2.02
    st
    2.02
    েই
    2.01
    Ꮤ
    1.86
    ány
    1.82
    amp
    1.81
    Ꮃ
    1.80
    굳
    1.77
    none
    1.76
    POSITIVE LOGITS
     Để
    2.26
    𝒅
    2.20
     גדול
    2.18
    રમાં
    2.16
     xúc
    2.15
    قاف
    2.15
    𝒑
    2.13
     संदीप
    2.12
     חו
    2.11
    𝒚
    2.08
    Activations Density 0.000%

    No Known Activations