© 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. 12-GEMMASCOPE-2-RES-262K
    7. 6603
    Prev
    Next
    INDEX
    Explanations

    python `def test`

    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
    I
    1.81
    A
    1.61
    1
    1.33
     and
    1.31
    U
    1.30
    J
    1.23
    AT
    1.21
    вал
    1.21
    V
    1.20
      
    1.20
    POSITIVE LOGITS
     fornisce
    1.65
    puede
    1.47
     byla
    1.44
     hitta
    1.44
     constituye
    1.43
    ள்ளதாக
    1.42
     ricevere
    1.42
     reconoce
    1.41
     recibe
    1.39
     ejecuta
    1.37
    Activations Density 0.266%

    No Known Activations