© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4263
    Prev
    Next
    INDEX
    Explanations

    do-while keywords and syntax

    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_12_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
     for
    1.38
     to
    1.21
     in
    1.16
     is
    1.10
     and
    1.05
     or
    1.01
    a
    0.99
     at
    0.96
     was
    0.96
     that
    0.95
    POSITIVE LOGITS
    أس
    1.04
     skapa
    1.02
    irà
    1.01
    əsi
    1.01
     trase
    1.00
     viviendo
    1.00
    Esto
    0.99
    ການ
    0.98
    हालांकि
    0.98
     bagaimana
    0.97
    Activations Density 0.109%

    No Known Activations