© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39109
    Prev
    Next
    INDEX
    Explanations

    discussing research aims and focus

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

    This neuron fires strongly on the formal introductory language of academic paper abstracts (e.g. “In this paper…,” “The aim is…,” “We introduce…”).

    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
     витами
    -1.33
     during
    -1.31
    if
    -1.24
    				
    -1.23
    					
    -1.16
     påvir
    -1.16
    __(
    -1.11
     if
    -1.10
    ).
    -1.08
     официаль
    -1.08
    POSITIVE LOGITS
     عاشقانه
    1.49
    亟
    1.48
    expiresIn
    1.45
    әһ
    1.43
    𓂂
    1.41
     enthou
    1.40
    Advertise
    1.38
    ävät
    1.38
     rengi
    1.37
    Esperamos
    1.34
    Activations Density 0.281%

    No Known Activations