© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1312
    Prev
    Next
    INDEX
    Explanations

    social units and areas

    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_16k_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
     及
    1.21
    และ
    1.20
    और
    1.20
    和
    1.20
     و
    1.20
     и
    1.19
     और
    1.15
     및
    1.11
    และความ
    1.10
     and
    1.09
    POSITIVE LOGITS
     ambayo
    0.96
    oresis
    0.93
    Ethnic
    0.93
    Semitism
    0.92
     émotion
    0.92
    oggles
    0.89
     pengetahuan
    0.88
     logika
    0.87
     monastic
    0.87
    ോഷ്യ
    0.87
    Activations Density 0.421%

    No Known Activations