© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 3325
    Prev
    Next
    INDEX
    Explanations

    it is or this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    -
    0.37
     mendatang
    0.34
    }}{\
    0.33
     else
    0.32
     uncomment
    0.32
     this
    0.31
    .")
    0.31
     /
    0.31
     MongoClient
    0.31
    ...")
    0.31
    POSITIVE LOGITS
     చాలా
    0.54
     લગભગ
    0.51
     rarely
    0.47
    лі
    0.46
    remely
    0.46
     often
    0.46
     spesso
    0.45
     খুবই
    0.44
     oldukça
    0.44
     biggest
    0.44
    Activations Density 0.016%

    No Known Activations