© 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-262K
    7. 7397
    Prev
    Next
    INDEX
    Explanations

    revealed mystery

    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_262k_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
      
    0.68
     standalone
    0.64
     dramatically
    0.62
    ↵
    0.60
     travers
    0.59
    ↵↵
    0.59
     cantilever
    0.58
     tailored
    0.58
     Land
    0.58
     across
    0.57
    POSITIVE LOGITS
    achtet
    1.05
    ſ
    1.03
    abhave
    0.98
    örter
    0.97
    aniu
    0.94
    issaient
    0.94
    zynarod
    0.93
    valment
    0.93
    ítulos
    0.92
    ioribus
    0.92
    Activations Density 0.015%

    No Known Activations