© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110542
    Prev
    Next
    INDEX
    Explanations

    training and professional roles

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

    The main thing this neuron detects is the names or key terms of professional training courses and certification programs.

    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
     that
    -1.51
     reveló
    -1.21
    utat
    -1.16
     pedimos
    -1.12
     new
    -1.11
     might
    -1.10
     beeind
    -1.10
     vorigen
    -1.08
     which
    -1.08
     genießen
    -1.06
    POSITIVE LOGITS
    вала
    1.13
                             
    1.13
                    
    1.13
                
    1.13
    </s>
    1.11
     suaminya
    1.08
     funktion
    1.05
     RUSS
    1.05
    rna
    1.05
    nshaw
    1.04
    Activations Density 0.106%

    No Known Activations