Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47795
    Prev
    Next
    INDEX
    Explanations

    code structure, syntax, identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ي
    1.24
    ो
    1.12
    т
    1.08
    oa
    1.00
    ით
    0.99
    ophilus
    0.96
     dizziness
    0.95
     شدہ
    0.95
    ুপ্ত
    0.94
    गत
    0.94
    POSITIVE LOGITS
     terap
    1.05
     valves
    1.01
    liga
    1.01
    켤
    1.00
     andre
    0.99
     maîtrise
    0.98
     transferencia
    0.97
     luego
    0.96
     confronti
    0.96
     ఉంటాయి
    0.95
    Activations Density 0.003%

    No Known Activations