© 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. 22-GEMMASCOPE-2-RES-16K
    7. 273
    Prev
    Next
    INDEX
    Explanations

    tell me:

    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_22_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
    抒
    0.89
    タグ
    0.88
     lesbians
    0.87
     Gog
    0.85
    许可证
    0.84
    帜
    0.84
     костю
    0.84
    卫
    0.83
    穿
    0.82
     সংগঠ
    0.81
    POSITIVE LOGITS
     compounding
    1.59
     चक्रवृद्धि
    1.54
     Compound
    1.45
     compound
    1.43
    compound
    1.39
    Compound
    1.36
     कंपाउंड
    1.35
     COMPO
    1.34
     CAGR
    1.31
     compounded
    1.30
    Activations Density 0.134%

    No Known Activations