© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17438
    Prev
    Next
    INDEX
    Explanations

    words ending in ge or ed

    np_acts-logits-general · gemini-2.5-flash-lite

    common word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
     Gh
    0.42
     Guad
    0.41
     Diagnose
    0.40
    𝐵
    0.40
     Jag
    0.40
     XY
    0.39
     Gareth
    0.39
     diagnose
    0.38
     Agg
    0.38
     Grill
    0.38
    POSITIVE LOGITS
    ge
    1.91
    GE
    1.71
    ges
    1.59
    ج
    1.36
    дж
    1.35
    ге
    1.34
    ged
    1.33
    je
    1.32
    ging
    1.30
    جه
    1.28
    Activations Density 0.077%

    No Known Activations