© 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. 34-GEMMASCOPE-RES-131K
    7. 70164
    Prev
    Next
    INDEX
    Explanations

    as far as concerned

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

    This neuron detects the idiomatic phrase “as far as … is concerned.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ствовал
    -0.83
    দ
    -0.83
     elegantes
    -0.80
    arky
    -0.80
    droid
    -0.78
    mirante
    -0.78
    hastly
    -0.77
    ченные
    -0.77
     podla
    -0.77
     Jeb
    -0.76
    POSITIVE LOGITS
     concerned
    4.41
    concerned
    3.22
     concern
    3.19
     concerns
    3.02
     Concerned
    2.70
    Concer
    2.64
    concern
    2.50
     Concern
    2.33
     CONCERN
    2.30
    Concern
    2.28
    Activations Density 0.051%

    No Known Activations