Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 45
    Prev
    Next
    INDEX
    Explanations

    0

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    1.41
    с
    1.20
    ва
    1.19
    نظر
    1.16
    ر
    1.09
    لای
    1.05
    ह
    1.05
    ن
    1.00
    لار
    0.98
    ни
    0.96
    POSITIVE LOGITS
    }}
    0.95
    ️⃣
    0.90
    ECO
    0.86
    í
    0.86
     Enrollment
    0.86
    ti
    0.84
     Crucible
    0.83
    ات
    0.82
    tain
    0.81
     shutout
    0.81
    Activations Density 0.455%

    No Known Activations