© 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. 2321
    Prev
    Next
    INDEX
    Explanations

    ec, EC, ecc, eck

    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
     nimic
    0.87
     imágenes
    0.83
     winding
    0.82
     searing
    0.79
     twisting
    0.78
    𝖾
    0.75
     disjoint
    0.75
     outfile
    0.74
     numerator
    0.74
     permutations
    0.74
    POSITIVE LOGITS
    ryption
    1.12
    اسم
    1.06
    stasy
    1.05
    uliar
    0.95
    lectic
    0.92
    اسي
    0.91
    ی
    0.90
     پید
    0.89
    clesiast
    0.89
    athlon
    0.88
    Activations Density 0.055%

    No Known Activations