© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44563
    Prev
    Next
    INDEX
    Explanations

    cytochromes P-450

    np_acts-logits-general · gemini-2.5-flash-lite

    The number "450" in various contexts, including measurements, values, or technical specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to numeric digit tokens—especially zeros appearing in numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -2.73
    and
    -2.61
    -
    -2.58
    in
    -2.22
     "
    -2.08
    O
    -2.06
      
    -2.05
     been
    -2.03
                    
    -2.03
          
    -2.03
    POSITIVE LOGITS
    觏
    2.80
    greifen
    2.31
    珰
    2.30
    führt
    2.25
    岽
    2.16
    媄
    2.06
    옻
    2.05
     liburan
    2.03
    zieht
    2.03
    ⡰
    1.99
    Activations Density 0.009%

    No Known Activations