© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 724
    Prev
    Next
    INDEX
    Explanations

    of- Service

    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_22_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
    की
    0.67
    ల
    0.67
    的
    0.65
     And
    0.65
     হাস
    0.64
     with
    0.63
     大
    0.62
    ፏ
    0.61
    の
    0.59
     о
    0.59
    POSITIVE LOGITS
    bilisi
    0.93
     buhay
    0.90
     teslim
    0.88
     magnon
    0.88
     gương
    0.86
    ↼
    0.85
     छात्राओं
    0.85
    trashItem
    0.83
     trono
    0.83
     orice
    0.83
    Activations Density 0.718%

    No Known Activations