© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    a qualified healthcare professional

    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
     отличается
    1.11
     repetition
    1.10
     })),
    1.07
     maggiore
    1.07
    ต้องการ
    1.04
     প্রশাস
    1.04
    简化
    1.03
    คน
    1.02
    ภา
    1.00
     чаще
    0.99
    POSITIVE LOGITS
    anel
    1.14
    ForKey
    1.07
    rite
    1.05
    뵈
    1.04
    Rite
    1.04
    ！！！
    1.03
     Jee
    1.03
     Gah
    1.02
     नष्ट
    1.02
    slit
    1.02
    Activations Density 0.421%

    No Known Activations