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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13572
    Prev
    Next
    INDEX
    Explanations

    at

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

    The neuron fires on numeric literals (both integers and decimals) in the code or license text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     to
    -1.36
     M
    -1.26
     S
    -1.20
     So
    -1.19
     P
    -1.18
    ardians
    -1.17
     I
    -1.15
     Go
    -1.14
     The
    -1.13
     Y
    -1.13
    POSITIVE LOGITS
    ↵↵
    2.58
    ώ
    1.38
    );
    
    
    1.37
     palanca
    1.22
    ↵↵↵
    1.22
     Aeropuerto
    1.20
     méret
    1.20
     şeyi
    1.20
     surtido
    1.18
     escritores
    1.17
    Activations Density 0.010%

    No Known Activations