© 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. 14823
    Prev
    Next
    INDEX
    Explanations

    objects with sentimental value

    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
     발생하는
    1.01
    積極的に
    0.93
     occuring
    0.89
     erfolgen
    0.88
    痿
    0.87
     erfolgt
    0.87
     utilisant
    0.87
     leverages
    0.87
     அடிப்பட
    0.86
    🥙
    0.86
    POSITIVE LOGITS
     purchased
    1.56
     heirloom
    1.53
     bought
    1.48
     sentimental
    1.46
     treasured
    1.46
     worn
    1.45
     antique
    1.37
     belonged
    1.33
     cherished
    1.33
     bequeathed
    1.30
    Activations Density 0.095%

    No Known Activations